本文详细分析了MySQL服务启动时遇到'The server quit without updating PID file'错误的原因，指出错误发生前提是通过服务脚本而非直接启动mysqld。文章探讨了服务脚本的工作原理，包括wait_for_pid函数在启动和停止过程中的作用，以及如何通过调整配置解决此问题。最后，提供了配置调整的建议，如设置basedir和conf变量，以及添加额外的启动参数。
很多童鞋在启动mysql的时候，碰到过这个错误，
首先，澄清一点，出现这个错误的前提是：通过服务脚本来启动mysql。通过mysqld_safe或mysqld启动mysql实例并不会报这个错误。
那么，出现这个错误的原因具体是什么呢？
哈哈，对分析过程不care的童鞋可直接跳到文末的总结部分~
总结
下面，来分析下mysql的服务启动脚本
脚本完整内容如下：
#!/bin/sh
# Copyright Abandoned 1996 TCX DataKonsult AB & Monty Program KB & Detron HB
# This file is public domain and comes with NO WARRANTY of any kind
# MySQL daemon start/stop script.
# Usually this is put in /etc/init.d (at least on machines SYSV R4 based
# systems) and linked to /etc/rc3.d/S99mysql and /etc/rc0.d/K01mysql.
# When this is done the mysql server will be started when the machine is
# started and shut down when the systems goes down.
# Comments to support chkconfig on RedHat Linux
# chkconfig: 2345 64 36
# description: A very fast and reliable SQL database engine.
# Comments to support LSB init script conventions
### BEGIN INIT INFO
# Provides: mysql
# Required-Start: $local_fs $network $remote_fs
# Should-Start: ypbind nscd ldap ntpd xntpd
# Required-Stop: $local_fs $network $remote_fs
# Default-Start: 2 3 4 5
# Default-Stop: 0 1 6
# Short-Description: start and stop MySQL
# Description: MySQL is a very fast and reliable SQL database engine.
### END INIT INFO
# If you install MySQL on some other places than /usr/local/mysql, then you
# have to do one of the following things for this script to work:
#
# - Run this script from within the MySQL installation directory
# - Create a /etc/my.cnf file with the following information:
# [mysqld]
# basedir=
# - Add the above to any other configuration file (for example ~/.my.ini)
# and copy my_print_defaults to /usr/bin
# - Add the path to the mysql-installation-directory to the basedir variable
# below.
#
# If you want to affect other MySQL variables, you should make your changes
# in the /etc/my.cnf, ~/.my.cnf or other MySQL configuration files.
# If you change base dir, you must also change datadir. These may get
# overwritten by settings in the MySQL configuration files.
basedir=
datadir=
# Default value, in seconds, afterwhich the script should timeout waiting
# for server start.
# Value here is overriden by value in my.cnf.
# 0 means don't wait at all
# Negative numbers mean to wait indefinitely
service_startup_timeout=900
# Lock directory for RedHat / SuSE.
lockdir='/var/lock/subsys'
lock_file_path="$lockdir/mysql"
# The following variables are only set for letting mysql.server find things.
# Set some defaults
mysqld_pid_file_path=
if test -z "$basedir"
then
basedir=/usr/local/mysql
bindir=/usr/local/mysql/bin
if test -z "$datadir"
then
datadir=/usr/local/mysql/data
fi
sbindir=/usr/local/mysql/bin
libexecdir=/usr/local/mysql/bin
else
bindir="$basedir/bin"
if test -z "$datadir"
then
datadir="$basedir/data"
fi
sbindir="$basedir/sbin"
libexecdir="$basedir/libexec"
fi
# datadir_set is used to determine if datadir was set (and so should be
# *not* set inside of the --basedir= handler.)
datadir_set=
#
# Use LSB init script functions for printing messages, if possible
#
lsb_functions="/lib/lsb/init-functions"
if test -f $lsb_functions ; then
. $lsb_functions
else
log_success_msg()
{
echo " SUCCESS! $@"
}
log_failure_msg()
{
echo " ERROR! $@"
}
fi
PATH="/sbin:/usr/sbin:/bin:/usr/bin:$basedir/bin"
export PATH
mode=$1 # start or stop
[ $# -ge 1 ] && shift
other_args="$*" # uncommon, but needed when called from an RPM upgrade action
# Expected: "--skip-networking --skip-grant-tables"
# They are not checked here, intentionally, as it is the resposibility
# of the "spec" file author to give correct arguments only.
case `echo "testing\c"`,`echo -n testing` in
*c*,-n*) echo_n= echo_c= ;;
*c*,*) echo_n=-n echo_c= ;;
*) echo_n= echo_c='\c' ;;
esac
parse_server_arguments() {
for arg do
case "$arg" in
--basedir=*) basedir=`echo "$arg" | sed -e 's/^[^=]*=//'`
bindir="$basedir/bin"
if test -z "$datadir_set"; then
datadir="$basedir/data"
fi
sbindir="$basedir/sbin"
libexecdir="$basedir/libexec"
;;
--datadir=*) datadir=`echo "$arg" | sed -e 's/^[^=]*=//'`
datadir_set=1
;;
--pid-file=*) mysqld_pid_file_path=`echo "$arg" | sed -e 's/^[^=]*=//'` ;;
--service-startup-timeout=*) service_startup_timeout=`echo "$arg" | sed -e 's/^[^=]*=//'` ;;
esac
done
}
wait_for_pid () {
verb="$1" # created | removed
pid="$2" # process ID of the program operating on the pid-file
pid_file_path="$3" # path to the PID file.
i=0
avoid_race_condition="by checking again"
while test $i -ne $service_startup_timeout ; do
case "$verb" in
'created')
# wait for a PID-file to pop into existence.
test -s "$pid_file_path" && i='' && break
;;
'removed')
# wait for this PID-file to disappear
test ! -s "$pid_file_path" && i='' && break
;;
*)
echo "wait_for_pid () usage: wait_for_pid created|removed pid pid_file_path"
exit 1
;;
esac
# if server isn't running, then pid-file will never be updated
if test -n "$pid"; then
if kill -0 "$pid" 2>/dev/null; then
: # the server still runs
else
# The server may have exited between the last pid-file check and now.
if test -n "$avoid_race_condition"; then
avoid_race_condition=""
continue # Check again.
fi
# there's nothing that will affect the file.
log_failure_msg "The server quit without updating PID file ($pid_file_path)."
return 1 # not waiting any more.
fi
fi
echo $echo_n ".$echo_c"
i=`expr $i + 1`
sleep 1
done
if test -z "$i" ; then
log_success_msg
return 0
else
log_failure_msg
return 1
fi
}
# Get arguments from the my.cnf file,
# the only group, which is read from now on is [mysqld]
if test -x ./bin/my_print_defaults
then
print_defaults="./bin/my_print_defaults"
elif test -x $bindir/my_print_defaults
then
print_defaults="$bindir/my_print_defaults"
elif test -x $bindir/mysql_print_defaults
then
print_defaults="$bindir/mysql_print_defaults"
else
# Try to find basedir in /etc/my.cnf
conf=/etc/my.cnf
print_defaults=
if test -r $conf
then
subpat='^[^=]*basedir[^=]*=\(.*\)$'
dirs=`sed -e "/$subpat/!d" -e 's//\1/' $conf`
for d in $dirs
do
d=`echo $d | sed -e 's/[ ]//g'`
if test -x "$d/bin/my_print_defaults"
then
print_defaults="$d/bin/my_print_defaults"
break
fi
if test -x "$d/bin/mysql_print_defaults"
then
print_defaults="$d/bin/mysql_print_defaults"
break
fi
done
fi
# Hope it's in the PATH ... but I doubt it
test -z "$print_defaults" && print_defaults="my_print_defaults"
fi
#
# Read defaults file from 'basedir'. If there is no defaults file there
# check if it's in the old (depricated) place (datadir) and read it from there
#
extra_args=""
if test -r "$basedir/my.cnf"
then
extra_args="-e $basedir/my.cnf"
else
if test -r "$datadir/my.cnf"
then
extra_args="-e $datadir/my.cnf"
fi
fi
parse_server_arguments `$print_defaults $extra_args mysqld server mysql_server mysql.server`
#
# Set pid file if not given
#
if test -z "$mysqld_pid_file_path"
then
mysqld_pid_file_path=$datadir/`hostname`.pid
else
case "$mysqld_pid_file_path" in
/* ) ;;
* ) mysqld_pid_file_path="$datadir/$mysqld_pid_file_path" ;;
esac
fi
case "$mode" in
'start')
# Start daemon
# Safeguard (relative paths, core dumps..)
cd $basedir
echo $echo_n "Starting MySQL"
if test -x $bindir/mysqld_safe
then
# Give extra arguments to mysqld with the my.cnf file. This script
# may be overwritten at next upgrade.
$bindir/mysqld_safe --datadir="$datadir" --pid-file="$mysqld_pid_file_path" $other_args >/dev/null 2>&1 &
wait_for_pid created "$!" "$mysqld_pid_file_path"; return_value=$?
# Make lock for RedHat / SuSE
if test -w "$lockdir"
then
touch "$lock_file_path"
fi
exit $return_value
else
log_failure_msg "Couldn't find MySQL server ($bindir/mysqld_safe)"
fi
;;
'stop')
# Stop daemon. We use a signal here to avoid having to know the
# root password.
if test -s "$mysqld_pid_file_path"
then
mysqld_pid=`cat "$mysqld_pid_file_path"`
if (kill -0 $mysqld_pid 2>/dev/null)
then
echo $echo_n "Shutting down MySQL"
kill $mysqld_pid
# mysqld should remove the pid file when it exits, so wait for it.
wait_for_pid removed "$mysqld_pid" "$mysqld_pid_file_path"; return_value=$?
else
log_failure_msg "MySQL server process #$mysqld_pid is not running!"
rm "$mysqld_pid_file_path"
fi
# Delete lock for RedHat / SuSE
if test -f "$lock_file_path"
then
rm -f "$lock_file_path"
fi
exit $return_value
else
log_failure_msg "MySQL server PID file could not be found!"
fi
;;
'restart')
# Stop the service and regardless of whether it was
# running or not, start it again.
if $0 stop $other_args; then
$0 start $other_args
else
log_failure_msg "Failed to stop running server, so refusing to try to start."
exit 1
fi
;;
'reload'|'force-reload')
if test -s "$mysqld_pid_file_path" ; then
read mysqld_pid < "$mysqld_pid_file_path"
kill -HUP $mysqld_pid && log_success_msg "Reloading service MySQL"
touch "$mysqld_pid_file_path"
else
log_failure_msg "MySQL PID file could not be found!"
exit 1
fi
;;
'status')
# First, check to see if pid file exists
if test -s "$mysqld_pid_file_path" ; then
read mysqld_pid < "$mysqld_pid_file_path"
if kill -0 $mysqld_pid 2>/dev/null ; then
log_success_msg "MySQL running ($mysqld_pid)"
exit 0
else
log_failure_msg "MySQL is not running, but PID file exists"
exit 1
fi
else
# Try to find appropriate mysqld process
mysqld_pid=`pidof $libexecdir/mysqld`
# test if multiple pids exist
pid_count=`echo $mysqld_pid | wc -w`
if test $pid_count -gt 1 ; then
log_failure_msg "Multiple MySQL running but PID file could not be found ($mysqld_pid)"
exit 5
elif test -z $mysqld_pid ; then
if test -f "$lock_file_path" ; then
log_failure_msg "MySQL is not running, but lock file ($lock_file_path) exists"
exit 2
fi
log_failure_msg "MySQL is not running"
exit 3
else
log_failure_msg "MySQL is running but PID file could not be found"
exit 4
fi
fi
;;
*)
# usage
basename=`basename "$0"`
echo "Usage: $basename {start|stop|restart|reload|force-reload|status} [ MySQL server options ]"
exit 1
;;
esac
exit 0
首先，定义相关参数
basedir=
datadir=
# Default value, in seconds, afterwhich the script should timeout waiting
# for server start.
# Value here is overriden by value in my.cnf.
# 0 means don't wait at all
# Negative numbers mean to wait indefinitely
service_startup_timeout=900
# Lock directory for RedHat / SuSE.
lockdir='/var/lock/subsys'
lock_file_path="$lockdir/mysql"
其中，
basedir 指的二进制压缩包解压后所在的目录，譬如/usr/local/mysql。
datadir 指的是数据目录
service_startup_timeout=900 定义mysql服务启动的时间限制，如果在900s中没有启动成功，则该脚本会退出。
lockdir='/var/lock/subsys'
关于/var/lock/subsys，网上的解释如下，后续会用到。
总的来说，系统关闭的过程(发出关闭信号，调用服务自身的进程)中会检查/var/lock/subsys下的文件，逐一关闭每个服务，如果某一运行的服务在/var/lock/subsys下没有相应的选项。在系统关闭的时候，会像杀死普通进程一样杀死这个服务。
通过察看/etc/rc.d/init.d下的脚本，可以发现每个服务自己操纵时都会去查看/var/lock/subsys下相应的服务。
很多程序需要判断是否当前已经有一个实例在运行，这个目录就是让程序判断是否有实例运行的标志，比如说xinetd，如果存在这个文件，表示已经有xinetd在运行了，否则就是没有，当然程序里面还要有相应的判断措施来真正确定是否有实例在运行。通常与该目录配套的还有/var/run目录，用来存放对应实例的PID，如果你写脚本的话，会发现这2个目录结合起来可以很方便的判断出许多服务是否在运行，运行的相关信息等等。
判断basedir和datadir
# Set some defaults
mysqld_pid_file_path=
if test -z "$basedir"
then
basedir=/usr/local/mysql
bindir=/usr/local/mysql/bin
if test -z "$datadir"
then
datadir=/usr/local/mysql/data
fi
sbindir=/usr/local/mysql/bin
libexecdir=/usr/local/mysql/bin
else
bindir="$basedir/bin"
if test -z "$datadir"
then
datadir="$basedir/data"
fi
sbindir="$basedir/sbin"
libexecdir="$basedir/libexec"
fi
其中，
mysqld_pid_file_path 指定pid文件的路径
-z string 判断字符串是否为空
如果basedir没有显示设置，则默认为/usr/local/mysql，这也是为什么很多mysql安装教程都推荐将mysql相关文件放到/usr/local/mysql下。
如果datadir没有显示设置，则默认为$basedir/data。
定义log_success_msg()和log_failure_msg()函数
首先，判断/lib/lsb/init-functions文件是否存在，如果存在，则使定义在init-functions文件中的所有shell函数在当前脚本中生效。
如果没有，则定义两个函数，一个用于打印成功日志，一个是打印错误日志。
在RHCS 6.7中，该文件并不存在，已被/etc/init.d/functions所替代。
#
# Use LSB init script functions for printing messages, if possible
#
lsb_functions="/lib/lsb/init-functions"
if test -f $lsb_functions ; then
. $lsb_functions
else
log_success_msg()
{
echo " SUCCESS! $@"
}
log_failure_msg()
{
echo " ERROR! $@"
}
fi
传递参数
将第一个参数传递给mode，剩下的参数传递给other_args
PATH="/sbin:/usr/sbin:/bin:/usr/bin:$basedir/bin"
export PATH
mode=$1 # start or stop
[ $# -ge 1 ] && shift
other_args="$*" # uncommon, but needed when called from an RPM upgrade action
# Expected: "--skip-networking --skip-grant-tables"
# They are not checked here, intentionally, as it is the resposibility
# of the "spec" file author to give correct arguments only.
case `echo "testing\c"`,`echo -n testing` in
*c*,-n*) echo_n= echo_c= ;;
*c*,*) echo_n=-n echo_c= ;;
*) echo_n= echo_c='\c' ;;
esac
解析配置文件中的参数
这个函数在脚本后面会涉及到。
主要涉及如下参数：--basedir，--datadir，--pid-file，--service-startup-timeout。
parse_server_arguments() {
for arg do
case "$arg" in
--basedir=*) basedir=`echo "$arg" | sed -e 's/^[^=]*=//'`
bindir="$basedir/bin"
if test -z "$datadir_set"; then
datadir="$basedir/data"
fi
sbindir="$basedir/sbin"
libexecdir="$basedir/libexec"
;;
--datadir=*) datadir=`echo "$arg" | sed -e 's/^[^=]*=//'`
datadir_set=1
;;
--pid-file=*) mysqld_pid_file_path=`echo "$arg" | sed -e 's/^[^=]*=//'` ;;
--service-startup-timeout=*) service_startup_timeout=`echo "$arg" | sed -e 's/^[^=]*=//'` ;;
esac
done
}
判断my_print_defaults的位置
首先，它判断当前路径下的bin目录中是否存在该可执行文件，如果不存在，则再判断$bindir(通常指的是$basedir/bin)目录下是否存在。
如果还是没有，则会判断/etc/my.cnf是否存在并且可读，如果是，则判断该配置文件中是否指定了basedir参数，
如果指定了，则取出该参数的值，并判断该值对应的目录中是否存在bin/my_print_defaults可执行文件
最后一步，如果在上述目录中实在没发现my_print_defaults文件，
索性就将print_defaults设置为"my_print_defaults"，寄希望于该命令在当前的PATH环境中。
# Get arguments from the my.cnf file,
# the only group, which is read from now on is [mysqld]
if test -x ./bin/my_print_defaults
then
print_defaults="./bin/my_print_defaults"
elif test -x $bindir/my_print_defaults
then
print_defaults="$bindir/my_print_defaults"
elif test -x $bindir/mysql_print_defaults
then
print_defaults="$bindir/mysql_print_defaults"
else
# Try to find basedir in /etc/my.cnf
conf=/etc/my.cnf
print_defaults=
if test -r $conf
then
subpat='^[^=]*basedir[^=]*=\(.*\)$'
dirs=`sed -e "/$subpat/!d" -e 's//\1/' $conf`
for d in $dirs
do
d=`echo $d | sed -e 's/[ ]//g'`
if test -x "$d/bin/my_print_defaults"
then
print_defaults="$d/bin/my_print_defaults"
break
fi
if test -x "$d/bin/mysql_print_defaults"
then
print_defaults="$d/bin/mysql_print_defaults"
break
fi
done
fi
# Hope it's in the PATH ... but I doubt it
test -z "$print_defaults" && print_defaults="my_print_defaults"
fi
查找默认的配置文件
-r file 如果文件可读，则为真
#
# Read defaults file from 'basedir'. If there is no defaults file there
# check if it's in the old (depricated) place (datadir) and read it from there
#
extra_args=""
if test -r "$basedir/my.cnf"
then
extra_args="-e $basedir/my.cnf"
else
if test -r "$datadir/my.cnf"
then
extra_args="-e $datadir/my.cnf"
fi
fi
解析配置文件中的参数
my_print_defaults的用法如下：
my_print_defaults --defaults-file=example.cnf client mysql
即读取配置文件中，client和mysql部分的参数配置，
具体在本脚本中，是读取mysqld，server，mysql_server，mysql.server四个部分的配置参数。
parse_server_arguments `$print_defaults $extra_args mysqld server mysql_server mysql.server`
设置pid file的路径
-z string 判断字符串是否为空
如果--pid-file没有在读取到的配置文件中设置或者脚本刚开始的mysqld_pid_file_path参数没有设置，
则pid file默认设置在datadir下，以主机名.pid命名。
如果该参数设置了，还需要进一步判断
如果该参数中带有斜杠，则代表给定的值带有路径，可直接使用。
如果该参数中没带路径，则代表给定的值只是pid的文件名，可将其设在datadir下。
#
# Set pid file if not given
#
if test -z "$mysqld_pid_file_path"
then
mysqld_pid_file_path=$datadir/`hostname`.pid
else
case "$mysqld_pid_file_path" in
/* ) ;;
* ) mysqld_pid_file_path="$datadir/$mysqld_pid_file_path" ;;
esac
fi
服务脚本start选项
首先，切换到$basedir中
其次，判断$basedir/bin中的mysqld_safe是否是可执行文件，如果是，则启动mysqld实例，如果不是，则报错退出。
那么，启动流程又是如何实现的呢？
首先，执行$bindir/mysqld_safe --datadir="$datadir" --pid-file="$mysqld_pid_file_path" $other_args >/dev/null 2>&1 &命令，启动mysqld实例。
注意到没有，mysqld_safe其实是在basedir中执行的，包括mysql初始化脚本mysql_install_db，也建议在basedir中执行，具体可参考：
分析MariaDB初始化脚本mysql_install_db
然后通过wait_for_pid函数进行判断，具体可见下文对于wait_for_pid函数的分析
判断完毕后，
查看$lockdir目录是否可写，可写的话，则在目录上创建一个文件。
case "$mode" in
'start')
# Start daemon
# Safeguard (relative paths, core dumps..)
cd $basedir
echo $echo_n "Starting MySQL"
if test -x $bindir/mysqld_safe
then
# Give extra arguments to mysqld with the my.cnf file. This script
# may be overwritten at next upgrade.
$bindir/mysqld_safe --datadir="$datadir" --pid-file="$mysqld_pid_file_path" $other_args >/dev/null 2>&1 &
wait_for_pid created "$!" "$mysqld_pid_file_path"; return_value=$?
# Make lock for RedHat / SuSE
if test -w "$lockdir"
then
touch "$lock_file_path"
fi
exit $return_value
else
log_failure_msg "Couldn't find MySQL server ($bindir/mysqld_safe)"
fi
;;
wait_for_pid函数
在利用mysqld_safe启动mysql实例后，会调用该参数
wait_for_pid created "$!" "$mysqld_pid_file_path"; return_value=$?
其中$!在shell中用于获取最后运行的后台Process的PID，具体在本例中，是mysqld_safe进程的pid。
因为第一个参数是created，所以会执行test -s "$pid_file_path" && i='' && break命令。
-s file 如果文件的长度不为零，则为真
该命令的意思是如果pid文件存在，则将变量i设置为空，并退出while循环。
然后执行如下判断，
if test -z "$i" ; then
log_success_msg
return 0
else
log_failure_msg
return 1
fi
如果$i为空，则打印成功日志，并退出脚本，很显然，在pid文件存在的情况下，会将变量i设置为空。
再来看看pid文件不存在的情况
首先，会判断$pid是否不为空(即if test -n "$pid")
如果不为空，则代表在执行完mysqld_safe后，已经捕捉到了该进程的pid。
在这种情况下，进一步通过kill -0 "$pid"确认该进程是否存在。
kill -0就是不发送任何信号,但是系统会进行错误检查,所以经常用来检查一个进程是否存在,当进程不存在时, kill -0 pid会返回错误
如果该进程存在，则不执行任何操作，直接跳到如下操作
echo $echo_n ".$echo_c"
i=`expr $i + 1`
sleep 1
将变量i加1，并sleep 1s。
然后，继续while循环，之所以这样做，是考虑到mysqld_safe已经执行，但是mysqld实例还在启动过程中，还没创建好pid文件。
一直到$1达到$service_startup_timeout定义的时长。
如果在while循环的过程中，通过kill -0 "$pid"判断到进程已经不存在了，
则会再判断一次，如果这次判断的结果依旧是pid file不存在，且进程不存在，则会执行
log_failure_msg "The server quit without updating PID file ($pid_file_path)."
这就是大名鼎鼎的“The server quit without updating PID file”的由来。
wait_for_pid () {
verb="$1" # created | removed
pid="$2" # process ID of the program operating on the pid-file
pid_file_path="$3" # path to the PID file.
i=0
avoid_race_condition="by checking again"
while test $i -ne $service_startup_timeout ; do
case "$verb" in
'created')
# wait for a PID-file to pop into existence.
test -s "$pid_file_path" && i='' && break
;;
'removed')
# wait for this PID-file to disappear
test ! -s "$pid_file_path" && i='' && break
;;
*)
echo "wait_for_pid () usage: wait_for_pid created|removed pid pid_file_path"
exit 1
;;
esac
# if server isn't running, then pid-file will never be updated
if test -n "$pid"; then
if kill -0 "$pid" 2>/dev/null; then
: # the server still runs
else
# The server may have exited between the last pid-file check and now.
if test -n "$avoid_race_condition"; then
avoid_race_condition=""
continue # Check again.
fi
# there's nothing that will affect the file.
log_failure_msg "The server quit without updating PID file ($pid_file_path)."
return 1 # not waiting any more.
fi
fi
echo $echo_n ".$echo_c"
i=`expr $i + 1`
sleep 1
done
if test -z "$i" ; then
log_success_msg
return 0
else
log_failure_msg
return 1
fi
}
服务脚本stop选项
首先，判断pid文件的长度是否不为零。
-s file 如果文件的长度不为零，则为真
此时，会通过pid文件获取mysqld进程的pid，注意，不是mysqld_safe进程的pid
然后，判断mysqld进程是否在正常运行，
如果是，则通过kill $mysqld_pid的方式来关闭mysqld进程
杀死进程最安全的方法是单纯使用kill命令，不加修饰符，不带标志。
标准的kill命令通常会终止有问题的进程，并把进程的资源释放给系统。然而，如果进程启动了子进程，只杀死父进程，子进程仍在运行，因此仍消耗资源。为了防止这些所谓的“僵尸进程”，应确保在杀死父进程之前，先杀死其所有的子进程。
然后，调用wait_for_pid函数进行判断，其实，wait_for_pid函数中设置avoid_race_condition变量的目的是为了stop选项，确实有可能出现，mysqld是在检查pid file之后，检查进程是否存活之前退出的。
如果mysqld进程没有正常运行，在会打印“MySQL server process #$mysqld_pid is not running!”信息，并删除pid文件。
如果在执行stop的时候，判断pid文件的长度为0，则会打印"MySQL server PID file could not be found!"信息。
所以，在pid文件不存在的情况下，通过服务脚本执行stop选项并不会关闭mysqld进程，这个时候，就可通过kill $mysqld_pid的方式来关闭mysqld进程。
'stop')
# Stop daemon. We use a signal here to avoid having to know the
# root password.
if test -s "$mysqld_pid_file_path"
then
mysqld_pid=`cat "$mysqld_pid_file_path"`
if (kill -0 $mysqld_pid 2>/dev/null)
then
echo $echo_n "Shutting down MySQL"
kill $mysqld_pid
# mysqld should remove the pid file when it exits, so wait for it.
wait_for_pid removed "$mysqld_pid" "$mysqld_pid_file_path"; return_value=$?
else
log_failure_msg "MySQL server process #$mysqld_pid is not running!"
rm "$mysqld_pid_file_path"
fi
# Delete lock for RedHat / SuSE
if test -f "$lock_file_path"
then
rm -f "$lock_file_path"
fi
exit $return_value
else
log_failure_msg "MySQL server PID file could not be found!"
fi
;;
服务脚本restart选项
首先，先执行stop操作，如果stop操作成功的话，则继续执行start操作。
如果stop操作失败的话，则会输出"Failed to stop running server, so refusing to try to start."信息，并退出脚本。
'restart')
# Stop the service and regardless of whether it was
# running or not, start it again.
if $0 stop $other_args; then
$0 start $other_args
else
log_failure_msg "Failed to stop running server, so refusing to try to start."
exit 1
fi
;;
服务脚本reload选项
首先，判断pid文件的长度是否为0，如果不为0，则将该文件中的值设置为mysqld_pid变量的值。
然后对该进程执行kill -HUP操作。
kill -HUP pid
pid 是进程标识。如果想要更改配置而不需停止并重新启动服务，请使用该命令。在对配置文件作必要的更改后，发出该命令以动态更新服务配置。
根据约定，当您发送一个挂起信号(信号 1 或 HUP)时，大多数服务器进程(所有常用的进程)都会进行复位操作并重新加载它们的配置文件。
如果pid文件的长度为0，则输出"MySQL PID file could not be found!"。
'reload'|'force-reload')
if test -s "$mysqld_pid_file_path" ; then
read mysqld_pid < "$mysqld_pid_file_path"
kill -HUP $mysqld_pid && log_success_msg "Reloading service MySQL"
touch "$mysqld_pid_file_path"
else
log_failure_msg "MySQL PID file could not be found!"
exit 1
fi
;;
服务脚本status选项
首先，判断pid文件长度是否为0，如果不是，则读取该文件中的值，并判断pid对应的进程是否运行正常，
如果运行正常，则输出"MySQL running"
如果不正常，则输出"MySQL is not running, but PID file exists"
如果pid文件的长度为0，则试图通过mysqld的启动命令来获取其pid，
这个时候，可能存在一个mysqld程序启动了多个实例，这会导致pid_count=`echo $mysqld_pid | wc -w`大于1。
这个时候，会输出"Multiple MySQL running but PID file could not be found"信息，并退出脚本。
如果mysqld_pid为空，则会继续判断"$lock_file_path"是否存在，如果存在，
则会输出"MySQL is not running, but lock file ($lock_file_path) exists"信息。
如果"$lock_file_path"不存在，则会输出"MySQL is not running"信息。
如果mysqld_pid等于1，则会输出"MySQL is running but PID file could not be found"信息。
'status')
# First, check to see if pid file exists
if test -s "$mysqld_pid_file_path" ; then
read mysqld_pid < "$mysqld_pid_file_path"
if kill -0 $mysqld_pid 2>/dev/null ; then
log_success_msg "MySQL running ($mysqld_pid)"
exit 0
else
log_failure_msg "MySQL is not running, but PID file exists"
exit 1
fi
else
# Try to find appropriate mysqld process
mysqld_pid=`pidof $libexecdir/mysqld`
# test if multiple pids exist
pid_count=`echo $mysqld_pid | wc -w`
if test $pid_count -gt 1 ; then
log_failure_msg "Multiple MySQL running but PID file could not be found ($mysqld_pid)"
exit 5
elif test -z $mysqld_pid ; then
if test -f "$lock_file_path" ; then
log_failure_msg "MySQL is not running, but lock file ($lock_file_path) exists"
exit 2
fi
log_failure_msg "MySQL is not running"
exit 3
else
log_failure_msg "MySQL is running but PID file could not be found"
exit 4
fi
fi
;;
服务脚本其它选项
如果脚本的第一个参数不是上述几个选项，则会输出Usage信息。
*)
# usage
basename=`basename "$0"`
echo "Usage: $basename {start|stop|restart|reload|force-reload|status} [ MySQL server options ]"
exit 1
;;
至此，mysql的服务脚本分析完毕~
总结
在通过服务脚本启动mysql的过程中，报“The server quit without updating PID file”错误，有两个条件
首先，pid文件不存在
其次，通过kill -0 $pid检查到进程并不存在
这个时候，只能通过mysql数据库的错误日志来定位。
服务脚本如果不做任何调整的话，默认的basedir是/usr/local/mysql，datadir是/usr/local/mysql/data
如果自己的mysql服务均不是默认路径，
则需要在该脚本中显式设置
经测试，需设置如下几处：
1. 设置basedir和添加conf变量
其中，conf指的是mysqld的配置文件，建议配置文件中显式指定basedir和datadir的值。
在这里，datadir可不设置，因为datadir可通过配置文件来获取。
但是basedir必须要指定，因为要首先根据basedir来判断my_print_deefauts命令
basedir=/usr/local/mysql-advanced-5.6.23-linux-glibc2.5-x86_64
datadir=
conf=/usr/local/mysql-advanced-5.6.23-linux-glibc2.5-x86_64/my_3308.cnf
2. 第256行，添加extra_args=" -c $conf"
extra_args=" -e $basedir/my.cnf.bak"
if test -r "$basedir/my.cnf"
then
extra_args="-e $basedir/my.cnf"
else
if test -r "$datadir/my.cnf"
then
extra_args="-e $datadir/my.cnf"
fi
fi
extra_args=" -c $conf"
3. 修改285行mysqld_safe的启动参数
将
$bindir/mysqld_safe --datadir="$datadir" --pid-file="$mysqld_pid_file_path" $other_args >/dev/null 2>&1 &
修改为，
$bindir/mysqld_safe --defaults-file="$conf" --datadir="$datadir" --pid-file="$mysqld_pid_file_path" $other_args >/dev/null 2>&1 &
主要是添加了--defaults-file选项
以上所述是小编给大家介绍的深度解析MySQL启动时报“The server quit without updating PID file”错误的原因，希望对大家有所帮助，如果大家有任何疑问请给我留言，小编会及时回复大家的。在此也非常感谢大家对脚本之家网站的支持！
扫一扫
4205
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
