Created
January 26, 2014 22:37
-
-
Save noskill/8640387 to your computer and use it in GitHub Desktop.
find requests per second
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import argparse | |
import re | |
import random | |
import datetime | |
import os | |
import sys | |
import time | |
import numpy | |
regex = re.compile(r"""^\[ | |
\d{2}\/[A-Za-z]{3}\/\d{4}:(\d{2}:\d{2}:\d{2})\s\+\d+\] # date | |
\spogoda\.yandex\.[a-z]+ # url | |
\s | |
\d+\.\d+\.\d+\.\d+ # ip address | |
\s\" | |
[A-Z]{3,4} # type of http request | |
.* | |
HTTP\/\d\.\d\"\s | |
(\d+) # http resp code | |
.*$""", re.VERBOSE) | |
SEC_IN_DAY = 3600 * 24 | |
def generate_log(path, lines): | |
patterns = [ | |
'[10/Oct/2012:{0} +0400] pogoda.yandex.by 178.122.164.78 "GET / HTTP/1.1" {1} "-" "Opera/9.80 (Windows NT 5.1; U; Edition Yx 01; ru) Presto/2.10.229 Version/11.60" "-" 0.008 - 1170\n', | |
'[10/Oct/2012:{0} +0400] pogoda.yandex.ru 212.193.232.183 "GET / HTTP/1.0" {1} "-" "-" "-" 0.011 - 1237\n', | |
'[10/Oct/2012:{0} +0400] pogoda.yandex.ru 78.46.121.182 "GET /kemerovo/details HTTP/1.1" {1} "http://pogoda.yandex.ru" "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)" "-" 0.314 - 93275\n', | |
'[10/Oct/2012:{0} +0400] pogoda.yandex.ru 93.158.129.212 "GET /astrahan/ HTTP/1.1" {1} "-" "Python-urllib/2.5" "-" 0.183 - 37160\n' | |
] | |
with open(path, 'at+') as f: | |
for i in range(lines): | |
p = patterns[random.randint(0,3)] | |
sec = random.randint(0, SEC_IN_DAY) | |
time_of_request = ('0' if sec < 36000 else '') + str(datetime.timedelta(seconds=sec)) | |
if len(time_of_request) != 8: | |
import pdb;pdb.set_trace() | |
resp_code = random.randint(200, 599) | |
f.write(p.format(time_of_request, resp_code)) | |
def read_log(path): | |
seconds = numpy.zeros(SEC_IN_DAY, dtype='int') | |
response_count = numpy.zeros(600, dtype='int') | |
code_5xx_count = 0 | |
with open(path, 'rt') as f: | |
for s in f: | |
match = regex.match(s) | |
event_time_strings = [int(x) for x in match.group(1).split(':')] | |
event_time = 3600 * event_time_strings[0] + 60 * event_time_strings[1] + event_time_strings[2] | |
code_index = int(match.group(2)) | |
seconds[event_time] += 1 | |
response_count[code_index] += 1 | |
code_5xx_count = sum(response_count[500:]) | |
return seconds, sum(response_count[500:]) | |
def parse_args(): | |
parser = argparse.ArgumentParser(description='generate and parse log') | |
group_lines = parser.add_mutually_exclusive_group() | |
parser.add_argument('--generate', action='store_true', default=False, help="generates new file") | |
parser.add_argument('--path', action='store', type=lambda x: os.path.abspath(x), help="path of file to write or to parse") | |
group_lines.add_argument('--lines', action='store', type=int, help="how many lines should generate") | |
group_lines.add_argument('--parse', action='store_true', default=False, help="parses log file") | |
return parser.parse_args() | |
args = parse_args() | |
if args.generate: | |
generate_log(args.path, args.lines) | |
if args.parse: | |
start = time.monotonic() | |
sec_count, resp_5xx_count = read_log(args.path) | |
end = time.monotonic() | |
print ("5xx response count: {0}".format(resp_5xx_count)) | |
print ('parse time: {0} seconds.'.format(end - start)) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment