线上问题排查常见脚本工具

show-busy-java-threads.sh

从所有的 Java 进程中找出最消耗 CPU 的线程（缺省5个），打印出其线程栈

用法

./show-busy-java-threads.sh
./show-busy-java-threads.sh -c <要显示的线程栈数>
./show-busy-java-threads.sh -c <要显示的线程栈数> -p <指定的Java Process>

脚本

#!/bin/bash
# @Function
# Find out the highest cpu consumed threads of java, and print the stack of these threads.
#
# @Usage
#   $ ./show-busy-java-threads.sh
#
# @author Jerry Lee

readonly PROG=`basename $0`
readonly -a COMMAND_LINE=("$0" "$@")

usage() {
    cat <<EOF
Usage: ${PROG} [OPTION]...
Find out the highest cpu consumed threads of java, and print the stack of these threads.
Example: ${PROG} -c 10

Options:
    -p, --pid       find out the highest cpu consumed threads from the specifed java process,
                    default from all java process.
    -c, --count     set the thread count to show, default is 5
    -h, --help      display this help and exit
EOF
    exit $1
}

readonly ARGS=`getopt -n "$PROG" -a -o c:p:h -l count:,pid:,help -- "$@"`
[ $? -ne 0 ] && usage 1
eval set -- "${ARGS}"

while true; do
    case "$1" in
    -c|--count)
        count="$2"
        shift 2
        ;;
    -p|--pid)
        pid="$2"
        shift 2
        ;;
    -h|--help)
        usage
        ;;
    --)
        shift
        break
        ;;
    esac
done
count=${count:-5}

redEcho() {
    [ -c /dev/stdout ] && {
        # if stdout is console, turn on color output.
        echo -ne "\033[1;31m"
        echo -n "$@"
        echo -e "\033[0m"
    } || echo "$@"
}

yellowEcho() {
    [ -c /dev/stdout ] && {
        # if stdout is console, turn on color output.
        echo -ne "\033[1;33m"
        echo -n "$@"
        echo -e "\033[0m"
    } || echo "$@"
}

blueEcho() {
    [ -c /dev/stdout ] && {
        # if stdout is console, turn on color output.
        echo -ne "\033[1;36m"
        echo -n "$@"
        echo -e "\033[0m"
    } || echo "$@"
}

# Check the existence of jstack command!
if ! which jstack &> /dev/null; then
    [ -z "$JAVA_HOME" ] && {
        redEcho "Error: jstack not found on PATH!"
        exit 1
    }
    ! [ -f "$JAVA_HOME/bin/jstack" ] && {
        redEcho "Error: jstack not found on PATH and $JAVA_HOME/bin/jstack file does NOT exists!"
        exit 1
    }
    ! [ -x "$JAVA_HOME/bin/jstack" ] && {
        redEcho "Error: jstack not found on PATH and $JAVA_HOME/bin/jstack is NOT executalbe!"
        exit 1
    }
    export PATH="$JAVA_HOME/bin:$PATH"
fi

readonly uuid=`date +%s`_${RANDOM}_$$

cleanupWhenExit() {
    rm /tmp/${uuid}_* &> /dev/null
}
trap "cleanupWhenExit" EXIT

printStackOfThreads() {
    local line
    local count=1
    while IFS=" " read -a line ; do
        local pid=${line[0]}
        local threadId=${line[1]}
        local threadId0x="0x`printf %x ${threadId}`"
        local user=${line[2]}
        local pcpu=${line[4]}

        local jstackFile=/tmp/${uuid}_${pid}

        [ ! -f "${jstackFile}" ] && {
            {
                if [ "${user}" == "${USER}" ]; then
                    jstack ${pid} > ${jstackFile}
                else
                    if [ $UID == 0 ]; then
                        sudo -u ${user} jstack ${pid} > ${jstackFile}
                    else
                        redEcho "[$((count++))] Fail to jstack Busy(${pcpu}%) thread(${threadId}/${threadId0x}) stack of java process(${pid}) under user(${user})."
                        redEcho "User of java process($user) is not current user($USER), need sudo to run again:"
                        yellowEcho "    sudo ${COMMAND_LINE[@]}"
                        echo
                        continue
                    fi
                fi
            } || {
                redEcho "[$((count++))] Fail to jstack Busy(${pcpu}%) thread(${threadId}/${threadId0x}) stack of java process(${pid}) under user(${user})."
                echo
                rm ${jstackFile}
                continue
            }
        }
        blueEcho "[$((count++))] Busy(${pcpu}%) thread(${threadId}/${threadId0x}) stack of java process(${pid}) under user(${user}):"
        sed "/nid=${threadId0x} /,/^$/p" -n ${jstackFile}
    done
}


ps -Leo pid,lwp,user,comm,pcpu --no-headers | {
    [ -z "${pid}" ] &&
    awk '$4=="java"{print $0}' ||
    awk -v "pid=${pid}" '$1==pid,$4=="java"{print $0}'
} | sort -k5 -r -n | head --lines "${count}" | printStackOfThreads

show-duplicate-java-classes

找出Java Lib（Java库，即Jar文件）或Class目录（类目录）中的重复类。

通过脚本参数指定Libs目录，查找目录下Jar文件，
收集Jar文件中Class文件以分析重复类。可以指定多个Libs目录。

注意，只会查找这个目录下Jar文件，不会查找子目录下Jar文件。
因为Libs目录一般不会用子目录再放Jar，这样也避免把去查找不期望Jar。
通过 -c 选项指定 Class 目录，直接收集这个目录下的 Class 文件以分析重复类。可以指定多个目录。

用法

# 查找当前目录下所有Jar中的重复类
./show-duplicate-java-classes

查找多个指定目录下所有Jar中的重复类
./show-duplicate-java-classes path/to/lib_dir1 /path/to/lib_dir2

查找多个指定Class目录下的重复类。 class 目录 通过 -c 选项指定
./show-duplicate-java-classes -c path/to/class_dir1 -c /path/to/class_dir2

查找指定Class目录和指定目录下所有Jar中的重复类的Jar
./show-duplicate-java-classes path/to/lib_dir1 /path/to/lib_dir2 -c path/to/class_dir1 -c path/to/class_dir2

脚本

#!/usr/bin/env python
# -*- coding: utf-8 -*-

__author__ = 'tg123'

from glob import glob
from os import walk
from zipfile import ZipFile
from os.path import relpath, isdir
from optparse import OptionParser


def list_jar_file_under_lib_dirs(libs):
    jar_files = set()
    for lib in libs:
        if isdir(lib):
            jar_files |= {f for f in glob(lib + '/*.jar')}
        else:
            jar_files.add(lib)
    return jar_files


def list_class_under_jar_file(jar_file):
    return {f for f in ZipFile(jar_file).namelist() if f.lower().endswith('.class')}


def list_class_under_class_dir(class_dir):
    return {relpath(dir_path + "/" + filename, class_dir)
            for dir_path, _, file_names in walk(class_dir)
            for filename in file_names if filename.lower().endswith('.class')}


def expand_2_class_path(jar_files, class_dirs):
    java_class_2_class_paths = {}
    # list all classes in jar files
    for jar_file in jar_files:
        for class_file in list_class_under_jar_file(jar_file):
            java_class_2_class_paths.setdefault(class_file, set()).add(jar_file)
    # list all classes in class dir
    for class_dir in class_dirs:
        for class_file in list_class_under_class_dir(class_dir):
            java_class_2_class_paths.setdefault(class_file, set()).add(class_dir)

    return java_class_2_class_paths, jar_files | set(class_dirs)


def find_duplicate_classes(java_class_2_class_paths):
    class_path_2_duplicate_classes = {}

    for java_class, class_paths in list(java_class_2_class_paths.items()):
        if len(class_paths) > 1:
            classes = class_path_2_duplicate_classes.setdefault(frozenset(class_paths), set())
            classes.add(java_class)

    return class_path_2_duplicate_classes


def print_class_paths(class_paths):
    print()
    print("=" * 80)
    print("class paths to find:")
    print("=" * 80)
    for idx, class_path in enumerate(class_paths):
        print(("%-3d: %s" % (idx + 1, class_path)))


if __name__ == '__main__':
    optionParser = OptionParser('usage: %prog '
                                '[-c class-dir1 [-c class-dir2] ...] '
                                '[lib-dir1|jar-file1 [lib-dir2|jar-file2] ...]')
    optionParser.add_option("-c", "--class-dir", dest="class_dirs", default=[], action="append", help="add class dir")
    options, libs = optionParser.parse_args()

    if not options.class_dirs and not libs:
        libs = ['.']

    java_class_2_class_paths, class_paths = expand_2_class_path(
        list_jar_file_under_lib_dirs(libs), options.class_dirs)

    class_path_2_duplicate_classes = find_duplicate_classes(java_class_2_class_paths)

    if not class_path_2_duplicate_classes:
        print("COOL! No duplicate classes found!")
        print_class_paths(class_paths)
        exit()

    print("Found duplicate classes in below class path:")
    for idx, jars in enumerate(class_path_2_duplicate_classes):
        print("%-3d(%d@%d): %s" % (idx + 1, len(class_path_2_duplicate_classes[jars]), len(jars), " ".join(jars)))

    print()
    print("=" * 80)
    print("Duplicate classes detail info:")
    print("=" * 80)
    for idx, (jars, classes) in enumerate(class_path_2_duplicate_classes.items()):
        print("%-3d(%d@%d): %s" % (idx + 1, len(class_path_2_duplicate_classes[jars]), len(jars), " ".join(jars)))
        for i, c in enumerate(classes):
            print("\t%-3d %s" % (i + 1, c))

    print_class_paths(class_paths)
    exit(1)

参考：https://github.com/oldratlee/...