Python 函数耗时异常自动化监控实战教程

import cProfile
# 程序开始的时候打开数据采集开关
pr = cProfile.Profile()
pr.enable()

# 在程序运行结束的时候dump性能数据到指定路径文件中，profliePath为保存文件的绝对路径参数
pr.dump_stats(profliePath)

import cProfile

# 程序开始的时候打开数据采集开关

pr = cProfile.Profile()

pr.enable()

​

# 在程序运行结束的时候dump性能数据到指定路径文件中，profliePath为保存文件的绝对路径参数

pr.dump_stats(profliePath)

import pstats 
# 读取性能数据 
pS = pstats.Stats(profliePath) 
# 根据函数自身累计耗时做排序 
pS.sort_stats('tottime') 
# 打印所有耗时函数信息 
pS.print_stats()
print_stats()输出示例：
79837 function calls (75565 primitive calls) in 37.311 seconds
Ordered by: internal time
ncalls  tottime  percall  cumtime  percall  filename:lineno(function)
 2050    30.167    0.015   30.167    0.015  {time.sleep}
   16     6.579    0.411    6.579    0.411  {select.select}
    1     0.142    0.142    0.142    0.142  {method 'do_handshake' of '_ssl._SSLSocket' objects}
  434     0.074    0.000    0.074    0.000  {method 'read' of '_ssl._SSLSocket' objects}
    1     0.062    0.062    0.062    0.062  {method 'connect' of '_socket.socket' objects}
   37     0.046    0.001    0.046    0.001  {posix.read}
   14     0.024    0.002    0.024    0.002  {posix.fork}

import pstats 

# 读取性能数据 

pS = pstats.Stats(profliePath) 

# 根据函数自身累计耗时做排序 

pS.sort_stats('tottime') 

# 打印所有耗时函数信息 

pS.print_stats()

print_stats()输出示例：

79837 function calls (75565 primitive calls) in 37.311 seconds

Ordered by: internal time

ncalls  tottime  percall  cumtime  percall  filename:lineno(function)

 2050    30.167    0.015   30.167    0.015  {time.sleep}

   16     6.579    0.411    6.579    0.411  {select.select}

    1     0.142    0.142    0.142    0.142  {method 'do_handshake' of '_ssl._SSLSocket' objects}

  434     0.074    0.000    0.074    0.000  {method 'read' of '_ssl._SSLSocket' objects}

    1     0.062    0.062    0.062    0.062  {method 'connect' of '_socket.socket' objects}

   37     0.046    0.001    0.046    0.001  {posix.read}

   14     0.024    0.002    0.024    0.002  {posix.fork}

# func————filename:lineno(function)
# cc ———— call count，调用次数 
# nc ———— ncalls
# tt ———— tottime
# ct ———— cumtime
# callers ———— 调用堆栈数组，每项数据包括了func, (cc, nc, tt, ct) 字段
for index in range(len(pS.fcn_list)): 
    func = pS.fcn_list[index] 
    cc, nc, tt, ct, callers = pS.stats[func]  
    print cc, nc, tt, ct, func, callers
    for func, (cc, nc, tt, ct) in callers.iteritems():
        print func，cc, nc, tt, ct

# func————filename:lineno(function)

# cc ———— call count，调用次数 

# nc ———— ncalls

# tt ———— tottime

# ct ———— cumtime

# callers ———— 调用堆栈数组，每项数据包括了func, (cc, nc, tt, ct) 字段

for index in range(len(pS.fcn_list)): 

    func = pS.fcn_list[index] 

    cc, nc, tt, ct, callers = pS.stats[func]  

    print cc, nc, tt, ct, func, callers

    for func, (cc, nc, tt, ct) in callers.iteritems():

        print func，cc, nc, tt, ct

brew install graphviz

brew install graphviz

import os
# 获取当前gprof2dot.py脚本路径
gprof2dotPath = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'gprof2dot.py')
# 函数调用栈结构图保存文件名路径，这边使用生成PNG图片结果
dumpProfPath = profliePath.replace("stats", "png")
dumpCmd = "python %s -f pstats %s | dot -Tpng -o %s" % (gprof2dotPath, profliePath, dumpProfPath)
os.popen(dumpCmd)

import os

# 获取当前gprof2dot.py脚本路径

gprof2dotPath = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'gprof2dot.py')

# 函数调用栈结构图保存文件名路径，这边使用生成PNG图片结果

dumpProfPath = profliePath.replace("stats", "png")

dumpCmd = "python %s -f pstats %s | dot -Tpng -o %s" % (gprof2dotPath, profliePath, dumpProfPath)

os.popen(dumpCmd)

from scipy import stats
import numpy
percallMean = numpy.mean(dataList) # 计算均值
# percallVar = numpy.var(dataList) # 求方差
percallStd = numpy.std(dataList) # 计算标准差
kstestResult = stats.kstest(dataList, 'norm', (percallMean, percallStd))
# 当pvalue值大于0.05为正态分布
if kstestResult[1] > 0.05:
    pass

from scipy import stats

import numpy

percallMean = numpy.mean(dataList) # 计算均值

# percallVar = numpy.var(dataList) # 求方差

percallStd = numpy.std(dataList) # 计算标准差

kstestResult = stats.kstest(dataList, 'norm', (percallMean, percallStd))

# 当pvalue值大于0.05为正态分布

if kstestResult[1] > 0.05:

    pass

import numpy
percallMean = numpy.mean(dataList)  # 计算均值
boxplotQ1 = numpy.percentile(dataList, 25)
boxplotQ2 = numpy.percentile(dataList, 75)
boxplotIQR = boxplotQ2 - boxplotQ1
upperLimit =  boxplotQ2 + 1.5 * boxplotIQR

import numpy

percallMean = numpy.mean(dataList)  # 计算均值

boxplotQ1 = numpy.percentile(dataList, 25)

boxplotQ2 = numpy.percentile(dataList, 75)

boxplotIQR = boxplotQ2 - boxplotQ1

upperLimit =  boxplotQ2 + 1.5 * boxplotIQR

# coding=utf-8
import os
import pstats
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
import traceback
from scipy import stats
import numpy

"""
汇总函数耗时平均值数据
"""
def dataSummary(array, fileName, fcn, percall):
    (funcPath, line, func) = fcn
    exists = False
    for item in array:
        if item["func"] == func and item["funcPath"] == funcPath and item["line"] == line:
            exists = True
            item["cost"].append({
                "percall": percall,
                "fileName": fileName
            })
    if not exists:
        array.append({
            "func": func,
            "funcPath": funcPath,
            "line": line,
            "cost": [{
                "percall": percall,
                "fileName": fileName
            }]
        })

"""
高斯函数计算Y值
"""
def gaussian(x, mu, delta):
    exp = numpy.exp(- numpy.power(x - mu, 2) / (2 * numpy.power(delta, 2)))
    c = 1 / (delta * numpy.sqrt(2 * numpy.pi))
    return c * exp

"""
读取汇总所有stats文件数据
"""
def readStatsFile(statFolder, filterData):
    for path, dir_list, file_list in os.walk(statFolder, "r"):
        for fileName in file_list:
            if fileName.find(".stats") > 0:
                fileAbsolutePath = os.path.join(path, fileName)
                pS = pstats.Stats(fileAbsolutePath)
             # 先对耗时数据从大到小进行排序
                pS.sort_stats('cumtime')
                # pS.print_stats()
                # 统计前100条耗时数据
                for index in range(100):
                    fcn = pS.fcn_list[index]
                    (funcPath, line, func) = fcn
                    # cc ———— call count，调用次数
                    # nc ———— ncalls，调用次数（只有一个数字时表示不存在递归；有斜杠分割数字时，后面的数字表示非递归调用的次数）
                    # tt ———— tottime，函数总计运行时间，除去函数中调用的子函数运行时间
                    # ct ———— cumtime，函数总计运行时间，含调用的子函数运行时间
                    cc, nc, tt, ct, callers = pS.stats[fcn]
                    # print fileName, func, cc, nc, tt, ct, callers
                    percall = ct / nc
                    # 只统计单次函数调用大于1毫秒的数据
                    if percall >= 0.001:
                        dataSummary(filterData, fileName, fcn, percall)

"""
绘制高斯函数曲线和安全阈值
"""
def drawGaussian(func, line, percallMean, threshold, percallList, dumpFolder):
    plt.title(func)
    plt.figure(figsize=(10, 8))
    for delta in [0.2, 0.5, 1]:
        gaussY = []
        gaussX = []
        for item in percallList:
            # 这边为了呈现正态曲线效果，减去平均值
            gaussX.append(item - percallMean)
            y = gaussian(item - percallMean, 0, delta)
            gaussY.append(y)
        plt.plot(gaussX, gaussY, label='sigma={}'.format(delta))
    # 绘制水位线
    plt.plot([threshold - percallMean, threshold - percallMean], [0, 5 * gaussian(percallMean, 0, 1)], color='red',
             linestyle="-", label="Threshold:" + str("%.5f" % threshold))
    plt.xlabel("Time(s)", fontsize=12)
    plt.legend()
    plt.tight_layout()
    # 可能不同类中包含相同的函数名，加上行数参数避免覆盖
    imagePath = dumpFolder + "cost_%s_%s.png" % (func, str(line))
    plt.savefig(imagePath)

"""
绘制耗时曲线和安全阈值
"""
def drawCurve(func, line, percallList, dumpFolder):
    boxplotQ1 = numpy.percentile(percallList, 25)
    boxplotQ2 = numpy.percentile(percallList, 75)
    boxplotIQR = boxplotQ2 - boxplotQ1
    upperLimit = boxplotQ2 + 1.5 * boxplotIQR
    # 不符合正态分布，绘制波动曲线
    timeArray = [i for i in range(len(percallList))]
    plt.title(dataItem["func"])
    plt.figure(figsize=(10, 8))
    # 绘制水位线
    plt.plot([0, len(percallList)], [upperLimit, upperLimit], color='red', linestyle="-",
             label="Threshold:" + str("%.5f" % upperLimit))
    plt.plot(timeArray, percallList, label=dataItem["func"] + "_" + str(dataItem["line"]))
    plt.ylabel("Time(s)", fontsize=12)
    plt.legend()
    plt.tight_layout()
    imagePath = dumpFolder + "cost_%s_%s.png" % (func, str(line))
    plt.savefig(imagePath)

if __name__ == "__main__":
    try:
        statFolder = "/Users/chenwenguan/Downloads/2aab7e17-a1b6-1253/"
        chartFolder = statFolder + "chart/"
        if not os.path.exists(chartFolder):
            os.mkdir(chartFolder)
        filterData = []
        readStatsFile(statFolder, filterData);
        for dataItem in filterData:
            percallList = map(lambda x: x["percall"], dataItem["cost"])
            func = dataItem["func"]
            line = dataItem["line"]
            # 样本个数大于20才进行绘制
            if len(percallList) > 20:
                percallMean = numpy.mean(percallList) # 计算均值
                # percallVar = numpy.var(percallMap) # 求方差
                percallStd = numpy.std(percallList)  # 计算标准差
                # pvalue值大于0.05为正太分布
                kstestResult = stats.kstest(percallList, 'norm', (percallMean, percallStd))
                print "percallStd:%s, pvalue:%s" % (percallStd, kstestResult[1])
                # 符合正态分布绘制分布曲线
                if kstestResult[1] > 0.05:
                    threshold = percallMean + 3 * percallStd
                    drawGaussian(func, line, percallMean, threshold, percallList, chartFolder)
                else:
                    drawCurve(func, line, percallList, chartFolder)
            else:
                pass
    except Exception:
        print 'exeption:' + traceback.format_exc()

# coding=utf-8

import os

import pstats

import matplotlib

matplotlib.use('Agg')

import matplotlib.pyplot as plt

import traceback

from scipy import stats

import numpy

​

"""

汇总函数耗时平均值数据

"""

def dataSummary(array, fileName, fcn, percall):

    (funcPath, line, func) = fcn

    exists = False

    for item in array:

        if item["func"] == func and item["funcPath"] == funcPath and item["line"] == line:

            exists = True

            item["cost"].append({

                "percall": percall,

                "fileName": fileName

            })

    if not exists:

        array.append({

            "func": func,

            "funcPath": funcPath,

            "line": line,

            "cost": [{

                "percall": percall,

                "fileName": fileName

            }]

        })

​

"""

高斯函数计算Y值

"""

def gaussian(x, mu, delta):

    exp = numpy.exp(- numpy.power(x - mu, 2) / (2 * numpy.power(delta, 2)))

    c = 1 / (delta * numpy.sqrt(2 * numpy.pi))

    return c * exp

​

"""

读取汇总所有stats文件数据

"""

def readStatsFile(statFolder, filterData):

    for path, dir_list, file_list in os.walk(statFolder, "r"):

        for fileName in file_list:

            if fileName.find(".stats") > 0:

                fileAbsolutePath = os.path.join(path, fileName)

                pS = pstats.Stats(fileAbsolutePath)

             # 先对耗时数据从大到小进行排序

                pS.sort_stats('cumtime')

                # pS.print_stats()

                # 统计前100条耗时数据

                for index in range(100):

                    fcn = pS.fcn_list[index]

                    (funcPath, line, func) = fcn

                    # cc ———— call count，调用次数

                    # nc ———— ncalls，调用次数（只有一个数字时表示不存在递归；有斜杠分割数字时，后面的数字表示非递归调用的次数）

                    # tt ———— tottime，函数总计运行时间，除去函数中调用的子函数运行时间

                    # ct ———— cumtime，函数总计运行时间，含调用的子函数运行时间

                    cc, nc, tt, ct, callers = pS.stats[fcn]

                    # print fileName, func, cc, nc, tt, ct, callers

                    percall = ct / nc

                    # 只统计单次函数调用大于1毫秒的数据

                    if percall >= 0.001:

                        dataSummary(filterData, fileName, fcn, percall)

​

"""

绘制高斯函数曲线和安全阈值

"""

def drawGaussian(func, line, percallMean, threshold, percallList, dumpFolder):

    plt.title(func)

    plt.figure(figsize=(10, 8))

    for delta in [0.2, 0.5, 1]:

        gaussY = []

        gaussX = []

        for item in percallList:

            # 这边为了呈现正态曲线效果，减去平均值

            gaussX.append(item - percallMean)

            y = gaussian(item - percallMean, 0, delta)

            gaussY.append(y)

        plt.plot(gaussX, gaussY, label='sigma={}'.format(delta))

    # 绘制水位线

    plt.plot([threshold - percallMean, threshold - percallMean], [0, 5 * gaussian(percallMean, 0, 1)], color='red',

             linestyle="-", label="Threshold:" + str("%.5f" % threshold))

    plt.xlabel("Time(s)", fontsize=12)

    plt.legend()

    plt.tight_layout()

    # 可能不同类中包含相同的函数名，加上行数参数避免覆盖

    imagePath = dumpFolder + "cost_%s_%s.png" % (func, str(line))

    plt.savefig(imagePath)

​

"""

绘制耗时曲线和安全阈值

"""

def drawCurve(func, line, percallList, dumpFolder):

    boxplotQ1 = numpy.percentile(percallList, 25)

    boxplotQ2 = numpy.percentile(percallList, 75)

    boxplotIQR = boxplotQ2 - boxplotQ1

    upperLimit = boxplotQ2 + 1.5 * boxplotIQR

    # 不符合正态分布，绘制波动曲线

    timeArray = [i for i in range(len(percallList))]

    plt.title(dataItem["func"])

    plt.figure(figsize=(10, 8))

    # 绘制水位线

    plt.plot([0, len(percallList)], [upperLimit, upperLimit], color='red', linestyle="-",

             label="Threshold:" + str("%.5f" % upperLimit))

    plt.plot(timeArray, percallList, label=dataItem["func"] + "_" + str(dataItem["line"]))

    plt.ylabel("Time(s)", fontsize=12)

    plt.legend()

    plt.tight_layout()

    imagePath = dumpFolder + "cost_%s_%s.png" % (func, str(line))

    plt.savefig(imagePath)

​

if __name__ == "__main__":

    try:

        statFolder = "/Users/chenwenguan/Downloads/2aab7e17-a1b6-1253/"

        chartFolder = statFolder + "chart/"

        if not os.path.exists(chartFolder):

            os.mkdir(chartFolder)

        filterData = []

        readStatsFile(statFolder, filterData);

        for dataItem in filterData:

            percallList = map(lambda x: x["percall"], dataItem["cost"])

            func = dataItem["func"]

            line = dataItem["line"]

            # 样本个数大于20才进行绘制

            if len(percallList) > 20:

                percallMean = numpy.mean(percallList) # 计算均值

                # percallVar = numpy.var(percallMap) # 求方差

                percallStd = numpy.std(percallList)  # 计算标准差

                # pvalue值大于0.05为正太分布

                kstestResult = stats.kstest(percallList, 'norm', (percallMean, percallStd))

                print "percallStd:%s, pvalue:%s" % (percallStd, kstestResult[1])

                # 符合正态分布绘制分布曲线

                if kstestResult[1] > 0.05:

                    threshold = percallMean + 3 * percallStd

                    drawGaussian(func, line, percallMean, threshold, percallList, chartFolder)

                else:

                    drawCurve(func, line, percallList, chartFolder)

            else:

                pass

    except Exception:

        print 'exeption:' + traceback.format_exc()