Merge branch 'master' into metrics_support

.gitignore

@@ -14,3 +14,5 @@ jtester.properties
 .idea/
 *.iml
 .DS_Store
+*.tar.gz
+*.rpm

deployer/src/main/java/com/alibaba/otter/canal/deployer/CanalController.java

@@ -379,7 +379,18 @@ public class CanalController {
     }
 
     private String getProperty(Properties properties, String key) {
-        return StringUtils.trim(properties.getProperty(StringUtils.trim(key)));
+        key = StringUtils.trim(key);
+        String value = System.getProperty(key);
+
+        if (value == null) {
+            value = System.getenv(key);
+        }
+
+        if (value == null) {
+            value = properties.getProperty(key);
+        }
+
+        return StringUtils.trim(value);
     }
 
     public void start() throws Throwable {

deployer/src/main/resources/canal.properties

@@ -3,7 +3,7 @@
 #################################################
 canal.id= 1
 canal.ip=
-canal.port= 11111
+canal.port=11111
 canal.zkServers=
 # flush data to zk
 canal.zookeeper.flush.period = 1000
@@ -59,6 +59,13 @@ canal.instance.parser.parallel = true
 ## disruptor ringbuffer size, must be power of 2
 canal.instance.parser.parallelBufferSize = 256
 
+# table meta tsdb info
+canal.instance.tsdb.enable=true
+canal.instance.tsdb.dir=${canal.file.data.dir:../conf}/${canal.instance.destination:}
+canal.instance.tsdb.url=jdbc:h2:${canal.instance.tsdb.dir}/h2;CACHE_SIZE=1000;MODE=MYSQL;
+canal.instance.tsdb.dbUsername=canal
+canal.instance.tsdb.dbPassword=canal
+
 #################################################
 ######### 		destinations		############# 
 #################################################

deployer/src/main/resources/example/instance.properties

@@ -1,11 +1,12 @@
 #################################################
-## mysql serverId
+## mysql serverId , v1.0.26+ will autoGen 
-canal.instance.mysql.slaveId=0
+# canal.instance.mysql.slaveId=0
+
+# enable gtid use true/false
+canal.instance.gtidon=false
 
 # position info
 canal.instance.master.address=127.0.0.1:3306
-# enable gtid use true/false
-canal.instance.gtidon=false
 canal.instance.master.journal.name=
 canal.instance.master.position=
 canal.instance.master.timestamp=
@@ -13,23 +14,21 @@ canal.instance.master.gtid=
 
 # table meta tsdb info
 canal.instance.tsdb.enable=true
-canal.instance.tsdb.dir=${canal.file.data.dir:../conf}/${canal.instance.destination:}
-canal.instance.tsdb.url=jdbc:h2:${canal.instance.tsdb.dir}/h2;CACHE_SIZE=1000;MODE=MYSQL;
 #canal.instance.tsdb.url=jdbc:mysql://127.0.0.1:3306/canal_tsdb
-canal.instance.tsdb.dbUsername=canal
+#canal.instance.tsdb.dbUsername=canal
-canal.instance.tsdb.dbPassword=canal
+#canal.instance.tsdb.dbPassword=canal
-
 
 #canal.instance.standby.address =
 #canal.instance.standby.journal.name =
 #canal.instance.standby.position = 
 #canal.instance.standby.timestamp =
 #canal.instance.standby.gtid=
+
 # username/password
 canal.instance.dbUsername=canal
 canal.instance.dbPassword=canal
-canal.instance.defaultDatabaseName=test
 canal.instance.connectionCharset=UTF-8
+
 # table regex
 canal.instance.filter.regex=.*\\..*
 # table black regex

deployer/src/main/resources/spring/default-instance.xml

@@ -149,7 +149,7 @@
 				<property name="address" value="${canal.instance.master.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		<property name="standbyInfo">
@@ -157,7 +157,7 @@
 				<property name="address" value="${canal.instance.standby.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		

deployer/src/main/resources/spring/file-instance.xml

@@ -134,7 +134,7 @@
 				<property name="address" value="${canal.instance.master.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		<property name="standbyInfo">
@@ -142,7 +142,7 @@
 				<property name="address" value="${canal.instance.standby.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		

deployer/src/main/resources/spring/group-instance.xml

@@ -131,7 +131,7 @@
 				<property name="address" value="${canal.instance.master1.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		<property name="standbyInfo">
@@ -139,7 +139,7 @@
 				<property name="address" value="${canal.instance.standby1.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		
@@ -229,7 +229,7 @@
 				<property name="address" value="${canal.instance.master2.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		<property name="standbyInfo">
@@ -237,7 +237,7 @@
 				<property name="address" value="${canal.instance.standby2.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		

deployer/src/main/resources/spring/local-instance.xml

@@ -114,7 +114,7 @@
 				<property name="address" value="${canal.instance.master.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		

deployer/src/main/resources/spring/memory-instance.xml

@@ -122,7 +122,7 @@
 				<property name="address" value="${canal.instance.master.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		<property name="standbyInfo">
@@ -130,7 +130,7 @@
 				<property name="address" value="${canal.instance.standby.address}" />
 				<property name="username" value="${canal.instance.dbUsername:retl}" />
 				<property name="password" value="${canal.instance.dbPassword:retl}" />
-				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:retl}" />
+				<property name="defaultDatabaseName" value="${canal.instance.defaultDatabaseName:test}" />
 			</bean>
 		</property>
 		

docker/Dockerfile

@@ -0,0 +1,67 @@
+FROM centos:centos6.7
+
+MAINTAINER agapple (jianghang115@gmail.com)
+
+# install system
+RUN \
+    /bin/cp -f /usr/share/zoneinfo/Asia/Shanghai /etc/localtime && \
+    echo 'root:Hello1234' | chpasswd && \
+    groupadd -r admin && useradd -g admin admin && \
+    yum install -y man && \
+    yum install -y dstat && \
+    yum install -y unzip && \
+    yum install -y nc && \
+    yum install -y openssh-server && \
+    yum install -y tar && \
+    yum install -y which && \
+    yum install -y wget && \
+    yum install -y perl && \
+    yum install -y file && \
+    ssh-keygen -q -N "" -t dsa -f /etc/ssh/ssh_host_dsa_key && \
+    ssh-keygen -q -N "" -t rsa -f /etc/ssh/ssh_host_rsa_key && \
+    sed -ri 's/session    required     pam_loginuid.so/#session    required     pam_loginuid.so/g' /etc/pam.d/sshd && \
+    sed -i -e 's/^#Port 22$/Port 2222/' /etc/ssh/sshd_config && \
+    mkdir -p /root/.ssh && chown root.root /root && chmod 700 /root/.ssh && \
+    yum install -y cronie && \
+    sed -i '/session required pam_loginuid.so/d' /etc/pam.d/crond && \
+    yum clean all && \
+    true
+
+# install canal
+COPY image/ /tmp/docker/
+COPY canal.deployer-*.tar.gz /home/admin/
+COPY jdk-8-linux-x64.rpm /tmp/
+
+RUN \
+    cp -R /tmp/docker/alidata /alidata && \
+    chmod +x /alidata/bin/* && \
+    mkdir -p /home/admin && \
+    cp -R /tmp/docker/admin/* /home/admin/  && \
+    /bin/cp -f alidata/bin/lark-wait /usr/bin/lark-wait && \
+
+    touch /var/lib/rpm/* && \ 
+    yum -y install /tmp/jdk-8-linux-x64.rpm && \
+    /bin/rm -f /tmp/jdk-8-linux-x64.rpm && \
+
+    echo "export JAVA_HOME=/usr/java/latest" >> /etc/profile && \
+    echo "export PATH=\$JAVA_HOME/bin:\$PATH" >> /etc/profile && \
+    /bin/mv /home/admin/bin/clean_log /etc/cron.d && \
+
+    mkdir -p /home/admin/canal-server && \
+    tar -xzvf /home/admin/canal.deployer-*.tar.gz -C /home/admin/canal-server && \
+    /bin/rm -f /home/admin/canal.deployer-*.tar.gz && \
+
+    mkdir -p home/admin/canal-server/logs  && \
+    chmod +x /home/admin/*.sh  && \
+    chmod +x /home/admin/bin/*.sh  && \
+    chown admin: -R /home/admin && \
+    yum clean all && \
+    true
+
+# 2222 sys , 8080 web , 8000 debug , 11111 canal
+EXPOSE 2222 11111 8000 8080
+
+WORKDIR /home/admin
+
+ENTRYPOINT [ "/alidata/bin/main.sh" ]
+CMD [ "/home/admin/app.sh" ]

docker/build.sh

@@ -0,0 +1,30 @@
+#!/bin/bash
+
+current_path=`pwd`
+case "`uname`" in
+    Darwin)
+        bin_abs_path=`cd $(dirname $0); pwd`
+        ;;
+    Linux)
+        bin_abs_path=$(readlink -f $(dirname $0))
+        ;;
+    *)
+        bin_abs_path=`cd $(dirname $0); pwd`
+        ;;
+esac
+BASE=${bin_abs_path}
+
+if [ ! -f $BASE/jdk*.rpm ] ; then
+    DOWNLOAD_LINK="http://download.oracle.com/otn-pub/java/jdk/8u181-b13/96a7b8442fe848ef90c96a2fad6ed6d1/jdk-8u181-linux-x64.tar.gz"
+    wget --no-cookies --no-check-certificate --header "Cookie: gpw_e24=xxx; oraclelicense=accept-securebackup-cookie" "$DOWNLOAD_LINK" -O $BASE/jdk-8-linux-x64.rpm
+fi
+
+cd $BASE/../ && mvn clean package -Dmaven.test.skip -Denv=release && cd $current_path ;
+
+if [ "$1" == "kafka" ] ; then
+	cp $BASE/../target/canal-kafka-*.tar.gz $BASE/
+	docker build --no-cache -t canal/canal-server $BASE/
+else 
+	cp $BASE/../target/canal.deployer-*.tar.gz $BASE/
+	docker build --no-cache -t canal/canal-server $BASE/
+fi

docker/image/admin/app.sh

@@ -0,0 +1,117 @@
+#!/bin/bash
+set -e
+
+source /etc/profile
+export JAVA_HOME=/usr/java/latest
+export PATH=$JAVA_HOME/bin:$PATH
+touch /tmp/start.log
+chown admin: /tmp/start.log
+chown -R admin: /home/admin/canal-server
+host=`hostname -i`
+
+# waitterm
+#   wait TERM/INT signal.
+#   see: http://veithen.github.io/2014/11/16/sigterm-propagation.html
+waitterm() {
+        local PID
+        # any process to block
+        tail -f /dev/null &
+        PID="$!"
+        # setup trap, could do nothing, or just kill the blocker
+        trap "kill -TERM ${PID}" TERM INT
+        # wait for signal, ignore wait exit code
+        wait "${PID}" || true
+        # clear trap
+        trap - TERM INT
+        # wait blocker, ignore blocker exit code
+        wait "${PID}" 2>/dev/null || true
+}
+
+# waittermpid "${PIDFILE}".
+#   monitor process by pidfile && wait TERM/INT signal.
+#   if the process disappeared, return 1, means exit with ERROR.
+#   if TERM or INT signal received, return 0, means OK to exit.
+waittermpid() {
+        local PIDFILE PID do_run error
+        PIDFILE="${1?}"
+        do_run=true
+        error=0
+        trap "do_run=false" TERM INT
+        while "${do_run}" ; do
+                PID="$(cat "${PIDFILE}")"
+                if ! ps -p "${PID}" >/dev/null 2>&1 ; then
+                        do_run=false
+                        error=1
+                else
+                        sleep 1
+                fi
+        done
+        trap - TERM INT
+        return "${error}"
+}
+
+
+function checkStart() {
+    local name=$1
+    local cmd=$2
+    local timeout=$3
+    cost=5
+    while [ $timeout -gt 0 ]; do
+        ST=`eval $cmd`
+        if [ "$ST" == "0" ]; then
+            sleep 1
+            let timeout=timeout-1
+            let cost=cost+1
+        elif [ "$ST" == "" ]; then
+            sleep 1
+            let timeout=timeout-1
+            let cost=cost+1
+        else
+            break
+        fi
+    done
+    echo "start $name successful"
+}
+
+
+function start_canal() {
+    echo "start canal ..."
+    serverPort=`perl -le 'print $ENV{"canal.port"}'`
+    if [ -z "$serverPort" ] ; then
+        serverPort=11111
+    fi
+
+    destination=`perl -le 'print $ENV{"canal.destinations"}'`
+    if [[ "$destination" =~ ',' ]]; then
+        echo "multi destination:$destination is not support"
+        exit 1;
+    else
+        mv /home/admin/canal-server/conf/example /home/admin/canal-server/conf/$destination
+    fi
+    su admin -c 'cd /home/admin/canal-server/bin/ && sh restart.sh 1>>/tmp/start.log 2>&1'
+    sleep 5
+    #check start
+    checkStart "canal" "nc 127.0.0.1 $serverPort -w 1 -z | wc -l" 30
+}
+
+function stop_canal() {
+    echo "stop canal"
+    su admin -c 'cd /home/admin/canal-server/bin/ && sh stop.sh 1>>/tmp/start.log 2>&1'
+    echo "stop canal successful ..."
+}
+
+echo "==> START ..."
+
+start_canal
+
+echo "==> START SUCCESSFUL ..."
+
+tail -f /dev/null &
+# wait TERM signal
+waitterm
+
+echo "==> STOP"
+
+stop_canal
+
+echo "==> STOP SUCCESSFUL ..."

docker/image/admin/bin/clean_log

@@ -0,0 +1,2 @@
+# cron clean log once per minute
+*/2 * * * * admin /home/admin/bin/clean_log.sh >>/tmp/clean_log.log 2>&1

docker/image/admin/bin/clean_log.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+
+# Global Settings
+PATH="$HOME/bin:/usr/local/sbin:/usr/local/bin:/sbin:/bin:/usr/sbin:/usr/bin:/usr/X11R6/bin:/root/bin"
+export PATH
+
+CUTOFF="85"
+#获取磁盘使用率最高的分区
+USAGE=$(df -h|awk 'NR>1 {gsub(/%$/,"",$5);print $5 }'|sort -nr|head -1)
+before=$USAGE
+
+baseClean(){
+    #删除tmp目录15天前的文件。
+    #更新文档时间戳
+    if [ -d /tmp/hsperfdata_admin ]
+    then
+        touch /tmp/hsperfdata_admin
+        touch /tmp/hsperfdata_admin/*
+    fi
+
+    find /tmp/ -type f -mtime +15 | xargs -t rm -rf >/dev/null 2>&1
+
+
+    now=$(df -h|awk 'NR>1 {gsub(/%$/,"",$5);print $5 }'|sort -nr|head -1)
+    echo "before:$before; now:$now"
+}
+
+CANAL_DIR="/home/admin/canal-server/logs"
+if [[ -d $CANAL_DIR ]]; then
+  USAGE=$(df -h|awk 'NR>1 {gsub(/%$/,"",$5);print $5 }'|sort -nr|head -1)
+  if [[ $USAGE -ge 90 ]]; then
+        find $CANAL_DIR -type f -mtime +7 | xargs rm -rf {}
+  fi
+  USAGE=$(df -h|awk 'NR>1 {gsub(/%$/,"",$5);print $5 }'|sort -nr|head -1)
+  if [[ $USAGE -ge 80 ]]; then
+        find $CANAL_DIR -type f -mtime +3 | xargs rm -rf {}
+  fi
+  USAGE=$(df -h|awk 'NR>1 {gsub(/%$/,"",$5);print $5 }'|sort -nr|head -1)
+  if [[ $USAGE -ge 80 ]]; then
+        find $CANAL_DIR -type d -empty -mtime +3 | grep -v canal | xargs rm -rf {}
+        find $CANAL_DIR -type f -iname '*.tmp' | xargs rm -rf {}
+  fi
+  baseClean
+  exit 0
+fi

docker/image/admin/health.sh

@@ -0,0 +1,13 @@
+#!/bin/sh
+CHECK_URL="http://127.0.0.1:8080/metrics"
+CHECK_POINT="success"
+CHECK_COUNT=`curl -s --connect-timeout 7 --max-time 7 $CHECK_URL | grep -c $CHECK_POINT`
+if [ $CHECK_COUNT -eq 0 ]; then
+    echo "[FAILED]"
+    status=0
+	error=1
+else
+    echo "[  OK  ]"
+    status=1
+	error=0
+fi

docker/image/alidata/bin/exec_rc_local.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+
+if [ "${SKIP_EXEC_RC_LOCAL}" = "YES" ] ; then
+	echo "skip /etc/rc.local: SKIP_EXEC_RC_LOCAL=${SKIP_EXEC_RC_LOCAL}"
+	exit
+fi
+
+if [ "${DOCKER_DEPLOY_TYPE}" = "HOST" ] ; then
+	echo "skip /etc/rc.local: DOCKER_DEPLOY_TYPE=${DOCKER_DEPLOY_TYPE}"
+	exit
+fi

docker/image/alidata/bin/lark-wait

@@ -0,0 +1,6 @@
+#!/bin/bash
+set -e
+
+chown admin: -R /home/admin/
+source /alidata/lib/proc.sh
+waitterm

docker/image/alidata/bin/main.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+
+[ -n "${DOCKER_DEPLOY_TYPE}" ] || DOCKER_DEPLOY_TYPE="VM"
+echo "DOCKER_DEPLOY_TYPE=${DOCKER_DEPLOY_TYPE}"
+
+# run init scripts
+for e in $(ls /alidata/init/*) ; do
+	[ -x "${e}" ] || continue
+	echo "==> INIT $e"
+	$e
+	echo "==> EXIT CODE: $?"
+done
+
+echo "==> INIT DEFAULT"
+service sshd start
+service crond start
+
+#echo "check hostname -i: `hostname -i`"
+#hti_num=`hostname -i|awk '{print NF}'`
+#if [ $hti_num -gt 1 ];then
+#    echo "hostname -i result error:`hostname -i`"
+#    exit 120
+#fi
+
+echo "==> INIT DONE"
+echo "==> RUN ${*}"
+exec "${@}"

docker/image/alidata/init/02init-sshd.sh

@@ -0,0 +1,19 @@
+#!/bin/bash
+
+# set port
+if [ -z "${SSHD_PORT}" ] ; then
+	SSHD_PORT=22
+	[ "${DOCKER_DEPLOY_TYPE}" = "HOST" ] && SSHD_PORT=2222
+fi
+
+sed -r -i '/^OPTIONS=/ d' /etc/sysconfig/sshd
+echo 'OPTIONS="-p '"${SSHD_PORT}"'"' >> /etc/sysconfig/sshd
+
+# set admin ssh pulic key
+if [ "${USE_ADMIN_PASSAGE}" = "YES" ] ; then
+    echo "set admin passage"
+    mkdir -p /home/admin/.ssh
+    chown admin:admin /home/admin/.ssh
+    chown admin:admin /home/admin/.ssh/authorized_keys
+    chmod 644 /home/admin/.ssh/authorized_keys
+fi

docker/image/alidata/init/fix-hosts.py

@@ -0,0 +1,66 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+#****************************************************************#
+# Create Date: 2017-01-06 17:58
+#***************************************************************#
+
+import socket
+import shutil
+from time import gmtime, strftime
+
+# get host_name
+host_name = socket.gethostname()
+tmp_file = "/tmp/.lark-fix-host.hosts"
+host_file = "/etc/hosts"
+bak_file_name = "/tmp/hosts-fix-bak.%s" % ( strftime("%Y-%m-%d_%H-%M-%S", gmtime()) )
+
+# load /etc/hosts file context
+FH = open(host_file,"r")
+file_lines = [ i.rstrip() for i in FH.readlines()]
+FH.close()
+file_lines_reverse = file_lines[::-1]
+new_lines = []
+bad_lines = []
+last_match_line = ""
+
+for line in file_lines_reverse:
+    if line.find(host_name) < 0:  # 不匹配的行直接跳过
+        new_lines.append(line + "\n")
+        continue
+
+    cols = line.split()
+    new_cols = []
+    if cols[0].startswith("#"): # 跳过已经注释掉的行
+        new_lines.append(line + "\n")
+        continue
+    for col in cols:
+        if not col == host_name: # 跳过不匹配的列
+            new_cols.append(col)
+            continue
+
+        if cols[0] == "127.0.0.1": # 如果第一列是 127.0.0.1 就跳过匹配的列, 防止 hostname -i 返回 127.0.0.1
+            continue
+
+        # 如果已经发现过匹配的列, 就丢掉重复的列
+        if not len(last_match_line) == 0:
+            continue
+
+        new_cols.append(col)
+        last_match_line = line
+
+    # 跳过 xx.xx.xx.xx hostname 这样的重复列
+    if len(new_cols) == 1:
+        continue
+
+    new_l = "%s\n" % " ".join(new_cols)
+    new_lines.append(new_l)
+
+# save tmp hosts
+
+FH2=file(tmp_file,"w+")
+FH2.writelines( new_lines[::-1])
+FH2.close()
+
+# mv to /etc/hosts
+shutil.copy(host_file, bak_file_name)
+shutil.move(tmp_file, host_file)

docker/image/alidata/lib/proc.sh

@@ -0,0 +1,40 @@
+# waitterm
+#   wait TERM/INT signal.
+#   see: http://veithen.github.io/2014/11/16/sigterm-propagation.html
+waitterm() {
+	local PID
+	# any process to block
+	tail -f /dev/null &
+	PID="$!"
+	# setup trap, could do nothing, or just kill the blocker
+	trap "kill -TERM ${PID}" TERM INT
+	# wait for signal, ignore wait exit code
+	wait "${PID}" || true
+	# clear trap
+	trap - TERM INT
+	# wait blocker, ignore blocker exit code
+	wait "${PID}" 2>/dev/null || true
+}
+
+# waittermpid "${PIDFILE}".
+#   monitor process by pidfile && wait TERM/INT signal.
+#   if the process disappeared, return 1, means exit with ERROR.
+#   if TERM or INT signal received, return 0, means OK to exit.
+waittermpid() {
+	local PIDFILE PID do_run error
+	PIDFILE="${1?}"
+	do_run=true
+	error=0
+	trap "do_run=false" TERM INT
+	while "${do_run}" ; do
+		PID="$(cat "${PIDFILE}")"
+		if ! ps -p "${PID}" >/dev/null 2>&1 ; then
+			do_run=false
+			error=1
+		else
+			sleep 1
+		fi
+	done
+	trap - TERM INT
+	return "${error}"
+}

docker/run.sh

@@ -0,0 +1,92 @@
+#!/bin/bash
+
+function usage() {
+    echo "Usage:"
+    echo "  run.sh [CONFIG]"
+    echo "example:"
+    echo "  run.sh -e canal.instance.master.address=127.0.0.1:3306 \\"
+    echo "         -e canal.instance.dbUsername=canal \\"
+    echo "         -e canal.instance.dbPassword=canal \\"
+    echo "         -e canal.instance.connectionCharset=UTF-8 \\"
+    echo "         -e canal.instance.tsdb.enable=true \\"
+    echo "         -e canal.instance.gtidon=false \\"
+    echo "         -e canal.instance.filter.regex=.*\\..* "
+    exit
+}
+
+function check_port() {
+    local port=$1
+    local TL=$(which telnet)
+    if [ -f $TL ]; then
+        data=`echo quit | telnet 127.0.0.1 $port| grep -ic connected`
+        echo $data
+        return
+    fi
+
+    local NC=$(which nc)
+    if [ -f $NC ]; then
+        data=`nc -z -w 1 127.0.0.1 $port | grep -ic succeeded`
+        echo $data
+        return
+    fi
+    echo "0"
+    return
+}
+
+function getMyIp() {
+    case "`uname`" in
+        Darwin)
+         myip=`echo "show State:/Network/Global/IPv4" | scutil | grep PrimaryInterface | awk '{print $3}' | xargs ifconfig | grep inet | grep -v inet6 | awk '{print $2}'`
+         ;;
+        *)
+         myip=`ip route get 1 | awk '{print $NF;exit}'`
+         ;;
+  esac
+  echo $myip
+}
+
+NET_MODE=""
+case "`uname`" in
+    Darwin)
+        bin_abs_path=`cd $(dirname $0); pwd`
+        ;;
+    Linux)
+        bin_abs_path=$(readlink -f $(dirname $0))
+        NET_MODE="--net=host"
+        ;;
+    *)
+        NET_MODE="--net=host"
+        bin_abs_path=`cd $(dirname $0); pwd`
+        ;;
+esac
+BASE=${bin_abs_path}
+if [ $# -eq 0 ]; then
+    usage
+elif [ "$1" == "-h" ] ; then
+    usage
+elif [ "$1" == "help" ] ; then
+    usage
+fi
+
+DATA="$BASE/data"
+mkdir -p $DATA
+CONFIG=${@:1}
+#VOLUMNS="-v $DATA:/home/admin/canal-server/logs"
+PORTLIST="8000 8080 2222 11111"
+PORTS=""
+for PORT in $PORTLIST ; do
+    #exist=`check_port $PORT`
+    exist="0"
+    if [ "$exist" == "0" ]; then
+        PORTS="$PORTS -p $PORT:$PORT"
+    else
+        echo "port $PORT is used , pls check"
+        exit 1
+    fi
+done
+
+MEMORY="-m 4096m"
+LOCALHOST=`getMyIp`
+cmd="docker run -it -h $LOCALHOST $CONFIG --name=canal-server $VOLUMNS $NET_MODE $PORTS $MEMORY canal/canal-server"
+echo $cmd
+eval $cmd

driver/src/main/java/com/alibaba/otter/canal/parse/driver/mysql/MysqlConnector.java

@@ -32,7 +32,7 @@ public class MysqlConnector {
     private String              password;
 
     private byte                charsetNumber     = 33;
-    private String              defaultSchema     = "retl";
+    private String              defaultSchema     = "test";
     private int                 soTimeout         = 30 * 1000;
     private int                 connTimeout       = 5 * 1000;
     private int                 receiveBufferSize = 16 * 1024;

instance/manager/src/main/java/com/alibaba/otter/canal/instance/manager/CanalInstanceWithManager.java

@@ -6,6 +6,7 @@ import java.util.ArrayList;
 import java.util.Collections;
 import java.util.List;
 
+import com.alibaba.otter.canal.meta.FileMixedMetaManager;
 import org.apache.commons.lang.StringUtils;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
@@ -20,13 +21,7 @@ import com.alibaba.otter.canal.filter.aviater.AviaterRegexFilter;
 import com.alibaba.otter.canal.instance.core.AbstractCanalInstance;
 import com.alibaba.otter.canal.instance.manager.model.Canal;
 import com.alibaba.otter.canal.instance.manager.model.CanalParameter;
-import com.alibaba.otter.canal.instance.manager.model.CanalParameter.DataSourcing;
+import com.alibaba.otter.canal.instance.manager.model.CanalParameter.*;
-import com.alibaba.otter.canal.instance.manager.model.CanalParameter.HAMode;
-import com.alibaba.otter.canal.instance.manager.model.CanalParameter.IndexMode;
-import com.alibaba.otter.canal.instance.manager.model.CanalParameter.MetaMode;
-import com.alibaba.otter.canal.instance.manager.model.CanalParameter.SourcingType;
-import com.alibaba.otter.canal.instance.manager.model.CanalParameter.StorageMode;
-import com.alibaba.otter.canal.instance.manager.model.CanalParameter.StorageScavengeMode;
 import com.alibaba.otter.canal.meta.MemoryMetaManager;
 import com.alibaba.otter.canal.meta.PeriodMixedMetaManager;
 import com.alibaba.otter.canal.meta.ZooKeeperMetaManager;
@@ -37,12 +32,7 @@ import com.alibaba.otter.canal.parse.inbound.AbstractEventParser;
 import com.alibaba.otter.canal.parse.inbound.group.GroupEventParser;
 import com.alibaba.otter.canal.parse.inbound.mysql.LocalBinlogEventParser;
 import com.alibaba.otter.canal.parse.inbound.mysql.MysqlEventParser;
-import com.alibaba.otter.canal.parse.index.CanalLogPositionManager;
+import com.alibaba.otter.canal.parse.index.*;
-import com.alibaba.otter.canal.parse.index.FailbackLogPositionManager;
-import com.alibaba.otter.canal.parse.index.MemoryLogPositionManager;
-import com.alibaba.otter.canal.parse.index.MetaLogPositionManager;
-import com.alibaba.otter.canal.parse.index.PeriodMixedLogPositionManager;
-import com.alibaba.otter.canal.parse.index.ZooKeeperLogPositionManager;
 import com.alibaba.otter.canal.parse.support.AuthenticationInfo;
 import com.alibaba.otter.canal.protocol.position.EntryPosition;
 import com.alibaba.otter.canal.sink.entry.EntryEventSink;
@@ -120,6 +110,11 @@ public class CanalInstanceWithManager extends AbstractCanalInstance {
             ZooKeeperMetaManager zooKeeperMetaManager = new ZooKeeperMetaManager();
             zooKeeperMetaManager.setZkClientx(getZkclientx());
             ((PeriodMixedMetaManager) metaManager).setZooKeeperMetaManager(zooKeeperMetaManager);
+        } else if (mode.isLocalFile()){
+            FileMixedMetaManager fileMixedMetaManager = new FileMixedMetaManager();
+            fileMixedMetaManager.setDataDir(parameters.getDataDir());
+            fileMixedMetaManager.setPeriod(parameters.getMetaFileFlushPeriod());
+            metaManager = fileMixedMetaManager;
         } else {
             throw new CanalException("unsupport MetaMode for " + mode);
         }

instance/manager/src/main/java/com/alibaba/otter/canal/instance/manager/model/CanalParameter.java

@@ -28,8 +28,10 @@ public class CanalParameter implements Serializable {
     private Long                     zkClusterId;                                                    // zk集群id，为管理方便
     private List<String>             zkClusters;                                                     // zk集群地址
 
+    private String                   dataDir                            = "../conf";                 // 默认本地文件数据的目录默认是conf
     // meta相关参数
     private MetaMode                 metaMode                           = MetaMode.MEMORY;           // meta机制
+    private Integer                  metaFileFlushPeriod                = 1000;                      // meta刷新间隔
 
     // storage存储
     private Integer                  transactionSize                    = 1024;                      // 支持处理的transaction事务大小
@@ -243,7 +245,9 @@ public class CanalParameter implements Serializable {
         /** 文件存储模式 */
         ZOOKEEPER,
         /** 混合模式，内存+文件 */
-        MIXED;
+        MIXED,
+        /** 本地文件存储模式*/
+        LOCAL_FILE;
 
         public boolean isMemory() {
             return this.equals(MetaMode.MEMORY);
@@ -256,6 +260,10 @@ public class CanalParameter implements Serializable {
         public boolean isMixed() {
             return this.equals(MetaMode.MIXED);
         }
+
+        public boolean isLocalFile(){
+            return this.equals(MetaMode.LOCAL_FILE);
+        }
     }
 
     public static enum IndexMode {
@@ -390,6 +398,22 @@ public class CanalParameter implements Serializable {
         return storageMode;
     }
 
+    public String getDataDir() {
+        return dataDir;
+    }
+
+    public void setDataDir(String dataDir) {
+        this.dataDir = dataDir;
+    }
+
+    public Integer getMetaFileFlushPeriod() {
+        return metaFileFlushPeriod;
+    }
+
+    public void setMetaFileFlushPeriod(Integer metaFileFlushPeriod) {
+        this.metaFileFlushPeriod = metaFileFlushPeriod;
+    }
+
     public void setStorageMode(StorageMode storageMode) {
         this.storageMode = storageMode;
     }

kafka/src/main/java/com/alibaba/otter/canal/kafka/producer/CanalKafkaStarter.java

@@ -121,7 +121,7 @@ public class CanalKafkaStarter {
                     Message message = server.getWithoutAck(clientIdentity, kafkaProperties.getCanalBatchSize()); // 获取指定数量的数据
                     long batchId = message.getId();
                     try {
-                        int size = message.getEntries().size();
+                        int size = message.isRaw() ?  message.getRawEntries().size() : message.getEntries().size();
                         if (batchId != -1 && size != 0) {
                             if (!StringUtils.isEmpty(destination.getTopic())) {
                                 Topic topic = new Topic();

parse/src/main/java/com/alibaba/otter/canal/parse/inbound/mysql/MysqlEventParser.java

@@ -648,6 +648,9 @@ public class MysqlEventParser extends AbstractMysqlEventParser implements CanalE
                 throw new CanalParseException("command : 'show master status' has an error! pls check. you need (at least one of) the SUPER,REPLICATION CLIENT privilege(s) for this operation");
             }
             EntryPosition endPosition = new EntryPosition(fields.get(0), Long.valueOf(fields.get(1)));
+            if (isGTIDMode && fields.size() > 4) {
+                endPosition.setGtid(fields.get(4));
+            }
             return endPosition;
         } catch (IOException e) {
             throw new CanalParseException("command : 'show master status' has an error!", e);

server/src/test/java/com/alibaba/otter/canal/server/CanalServerWithEmbedded_FileModeTest.java

@@ -0,0 +1,53 @@
+package com.alibaba.otter.canal.server;
+
+import java.net.InetSocketAddress;
+import java.util.Arrays;
+
+import com.alibaba.otter.canal.instance.manager.model.Canal;
+import com.alibaba.otter.canal.instance.manager.model.CanalParameter;
+import com.alibaba.otter.canal.instance.manager.model.CanalParameter.*;
+
+public class CanalServerWithEmbedded_FileModeTest extends BaseCanalServerWithEmbededTest {
+
+    protected Canal buildCanal() {
+        Canal canal = new Canal();
+        canal.setId(1L);
+        canal.setName(DESTINATION);
+        canal.setDesc("my standalone server test ");
+
+        CanalParameter parameter = new CanalParameter();
+
+        parameter.setMetaMode(MetaMode.LOCAL_FILE);
+        parameter.setDataDir("./conf");
+        parameter.setMetaFileFlushPeriod(1000);
+        parameter.setHaMode(HAMode.HEARTBEAT);
+        parameter.setIndexMode(IndexMode.MEMORY_META_FAILBACK);
+
+        parameter.setStorageMode(StorageMode.MEMORY);
+        parameter.setMemoryStorageBufferSize(32 * 1024);
+
+        parameter.setSourcingType(SourcingType.MYSQL);
+        parameter.setDbAddresses(Arrays.asList(new InetSocketAddress(MYSQL_ADDRESS, 3306),
+            new InetSocketAddress(MYSQL_ADDRESS, 3306)));
+        parameter.setDbUsername(USERNAME);
+        parameter.setDbPassword(PASSWORD);
+        parameter.setPositions(Arrays.asList("{\"journalName\":\"mysql-bin.000001\",\"position\":332L,\"timestamp\":\"1505998863000\"}",
+            "{\"journalName\":\"mysql-bin.000001\",\"position\":332L,\"timestamp\":\"1505998863000\"}"));
+
+        parameter.setSlaveId(1234L);
+
+        parameter.setDefaultConnectionTimeoutInSeconds(30);
+        parameter.setConnectionCharset("UTF-8");
+        parameter.setConnectionCharsetNumber((byte) 33);
+        parameter.setReceiveBufferSize(8 * 1024);
+        parameter.setSendBufferSize(8 * 1024);
+
+        parameter.setDetectingEnable(false);
+        parameter.setDetectingIntervalInSeconds(10);
+        parameter.setDetectingRetryTimes(3);
+        parameter.setDetectingSQL(DETECTING_SQL);
+
+        canal.setCanalParameter(parameter);
+        return canal;
+    }
+}