#!/usr/bin/env python2
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import sys, os, subprocess
from terminalsize import get_terminal_size
from time import time, sleep
import re
import fnmatch

def load_colors():
    color_script_fn = os.path.join(os.path.dirname(__file__), "color.enabled.sh")
    with open(color_script_fn) as f:
        return dict([(k,v.split("'")[1].replace('\e[', "\033[")) for k,v in [x.strip().split('=') for x in f.readlines() if x.strip() and not x.strip().startswith('#')]])

Color=load_colors()
if int(os.environ.get("HIBENCH_PRINTFULLLOG", 0)):
    Color['ret'] = os.linesep
else:
    Color['ret']='\r'

tab_matcher = re.compile("\t")
tabstop = 8
def replace_tab_to_space(s):
    def tab_replacer(match):
        pos = match.start()
        length = pos % tabstop
        if not length: length += tabstop
        return " " * length
    return tab_matcher.sub(tab_replacer, s)

class _Matcher:
    hadoop = re.compile(r"^.*map\s*=\s*(\d+)%,\s*reduce\s*=\s*(\d+)%.*$")
    hadoop2 = re.compile(r"^.*map\s+\s*(\d+)%\s+reduce\s+\s*(\d+)%.*$")
    spark = re.compile(r"^.*finished task \S+ in stage \S+ \(tid \S+\) in.*on.*\((\d+)/(\d+)\)\s*$")
    def match(self, line):
        for p in [self.hadoop, self.hadoop2]:
            m = p.match(line)
            if m:
                return (float(m.groups()[0]) + float(m.groups()[1]))/2

        for p in [self.spark]:
            m = p.match(line)
            if m:
                return float(m.groups()[0]) / float(m.groups()[1]) * 100

matcher = _Matcher()

def show_with_progress_bar(line, progress, line_width):
    """
    Show text with progress bar.

    @progress:0-100
    @line: text to show
    @line_width: width of screen
    """
    pos = int(line_width * progress / 100)
    if len(line) < line_width:
        line = line + " " * (line_width - len(line))
    line = "{On_Yellow}{line_seg1}{On_Blue}{line_seg2}{Color_Off}{ret}".format(
        line_seg1 = line[:pos], line_seg2 = line[pos:], **Color)
    sys.stdout.write(line)

def execute(workload_result_file, command_lines):
    proc = subprocess.Popen(" ".join(command_lines), shell=True, bufsize=1, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
    count = 100
    last_time=0
    log_file = open(workload_result_file, 'w')
    # see http://stackoverflow.com/a/4417735/1442961
    lines_iterator = iter(proc.stdout.readline, b"")
    for line in lines_iterator:
        count += 1
        if count > 100 or time()-last_time>1: # refresh terminal size for 100 lines or each seconds
            count, last_time = 0, time()
            width, height = get_terminal_size()
            width -= 1

        try:
            line = line.rstrip()
            log_file.write(line+"\n")
            log_file.flush()
        except KeyboardInterrupt:
            proc.terminate()
            break
        line = line.decode('utf-8')
        line = replace_tab_to_space(line)
        #print "{Red}log=>{Color_Off}".format(**Color), line
        lline = line.lower()

        def table_not_found_in_log(line):
            table_not_found_pattern = "*Table * not found*"
            regex = fnmatch.translate(table_not_found_pattern)
            reobj = re.compile(regex)
            if reobj.match(line):
                return True
            else:
                return False

        def database_default_exist_in_log(line):
            database_default_already_exist = "Database default already exists"
            if database_default_already_exist in line:
                return True
            else:
                return False

        def uri_with_key_not_found_in_log(line):
            uri_with_key_not_found = "Could not find uri with key [dfs.encryption.key.provider.uri]"
            if uri_with_key_not_found in line:
                return True
            else:
                return False

        if ('error' in lline) and lline.lstrip() == lline:
            #Bypass hive 'error's and KeyProviderCache error
            bypass_error_condition = table_not_found_in_log or database_default_exist_in_log(lline) or uri_with_key_not_found_in_log(lline)
            if not bypass_error_condition:
                COLOR = "Red"
                sys.stdout.write((u"{%s}{line}{Color_Off}{ClearEnd}\n" % COLOR).format(line=line,**Color).encode('utf-8'))

        else:
            if len(line) >= width:
                line = line[:width-4]+'...'
            progress = matcher.match(lline)
            if progress is not None:
                show_with_progress_bar(line, progress, width)
            else:
                sys.stdout.write(u"{line}{ClearEnd}{ret}".format(line=line, **Color).encode('utf-8'))
        sys.stdout.flush()
    print
    log_file.close()
    try:
        proc.wait()
    except KeyboardInterrupt:
        proc.kill()
        return 1
    return proc.returncode

def test_progress_bar():
    for i in range(101):
        show_with_progress_bar("test progress : %d" % i, i, 80)
        sys.stdout.flush()

        sleep(0.05)

if __name__=="__main__":
    sys.exit(execute(workload_result_file=sys.argv[1],
                     command_lines=sys.argv[2:]))
#    test_progress_bar()

HiBench成长笔记——(10) 分析源码execute_with_log.py的更多相关文章

  1. HiBench成长笔记——(9) 分析源码monitor.py

    monitor.py 是主监控程序,将监控数据写入日志,并统计监控数据生成HTML统计展示页面: #!/usr/bin/env python2 # Licensed to the Apache Sof ...

  2. HiBench成长笔记——(8) 分析源码workload_functions.sh

    workload_functions.sh 是测试程序的入口,粘连了监控程序 monitor.py 和 主运行程序: #!/bin/bash # Licensed to the Apache Soft ...

  3. HiBench成长笔记——(11) 分析源码run.sh

    #!/bin/bash # Licensed to the Apache Software Foundation (ASF) under one or more # contributor licen ...

  4. HiBench成长笔记——(5) HiBench-Spark-SQL-Scan源码分析

    run.sh #!/bin/bash # Licensed to the Apache Software Foundation (ASF) under one or more # contributo ...

  5. Hadoop学习笔记(10) ——搭建源码学习环境

    Hadoop学习笔记(10) ——搭建源码学习环境 上一章中,我们对整个hadoop的目录及源码目录有了一个初步的了解,接下来计划深入学习一下这头神象作品了.但是看代码用什么,难不成gedit?,单步 ...

  6. CentOS 7运维管理笔记(10)----MySQL源码安装

    MySQL可以支持多种平台,如Windows,UNIX,FreeBSD或其他Linux系统.本篇随笔记录在CentOS 7 上使用源码安装MySQL的过程. 1.下载源码 选择使用北理工的镜像文件: ...

  7. memcached学习笔记——存储命令源码分析下篇

    上一篇回顾:<memcached学习笔记——存储命令源码分析上篇>通过分析memcached的存储命令源码的过程,了解了memcached如何解析文本命令和mencached的内存管理机制 ...

  8. memcached学习笔记——存储命令源码分析上篇

    原创文章,转载请标明,谢谢. 上一篇分析过memcached的连接模型,了解memcached是如何高效处理客户端连接,这一篇分析memcached源码中的process_update_command ...

  9. kernel 3.10内核源码分析--hung task机制

    kernel 3.10内核源码分析--hung task机制 一.相关知识: 长期以来,处于D状态(TASK_UNINTERRUPTIBLE状态)的进程 都是让人比较烦恼的问题,处于D状态的进程不能接 ...

随机推荐

  1. 第二节: Vuejs常用特性1

    一. 常用特性 1. 表单元素 通过 v-model指令绑定 输入框.单选/多选框.下拉框.文本框 2. 表单域修饰符 (1) .number:转换成数值,如果输入的是非数字字符串时,无法进行转换 ( ...

  2. python字符串操作方法详解

      字符串 字符串序列用于表示和存储文本,python中字符串是不可变对象.字符串是一个有序的字符的集合,用于存储和表示基本的文本信息,一对单,双或三引号中间包含的内容称之为字符串.其中三引号可以由多 ...

  3. slice 、 substr 、replace

    slice( 参数1  [,参数2] )        (注意不要让[参数1]下标越过[参数2]下标,否则会得到空字符串,且[参数2]是不包含在截取范围内的) 参数1:截取字符的[起始下标]. 值为正 ...

  4. 【C++初学者自学笔记三】哑元函数、缺省参数、内联函数(模块二,PS:需要用到重载函数)

    一,哑元函数:一个函数的参数只有类型没有名字的则这个参数称之为哑元.类似于void fun(int); 功能:1保持向前的兼容性,比方说我们需要做成一个成品,然后成品是会不断的更新第一代第二代,当我们 ...

  5. druid监控sql完整版

    利用Druid实现应用和SQL监控 一.关于Druid Druid是一个JDBC组件,它包括三部分: DruidDriver 代理Driver,能够提供基于Filter-Chain模式的插件体系. D ...

  6. Unknown column '××' in 'where clause',出现这个问题,如何处理?

    stmt.executeQuery("select * from user where username = " + name); 执行上述代码就会引发该错误. 原因是:拼凑sql ...

  7. Vases and Flowers-HDU4614 二分+线段树

    题意: 给你N个花瓶,编号是0  到 N - 1 ,一开始每个花瓶都是空的,你有两个操作: 第一个操作: 从第x个花瓶起开始插花,总共插y束,如果遇到花瓶中有花就跳过这个花瓶,直到花插完或者 插到第N ...

  8. F: Horse Pro 马走棋盘 BFS

    F: Horse Pro 豆豆也已经开始学着玩象棋了,现在豆豆已经搞清楚马的走法了,但是豆豆不能确定能否在 100 步以内从一个点到达另一个点(假设棋盘无限大). Input 第一行输入两个整数 x1 ...

  9. 关于盒模型的外边距padding和内边距margin

    边框border属性值  solid实线   dashed虚线   dotted点线   double双实线 /* 内边距 */padding:20px 30px 30px 30px;若有四个值代表  ...

  10. 认识gets&read(buffer over flow is bof)

    gets不会检查输入的长度,从而有数据覆盖的风险,