今天就跟大家聊聊有关Nginx Httpcode的分析脚本是什么,可能很多人都不太了解,为了让大家更加了解,小编给大家总结了以下内容,希望大家根据这篇文章可以有所收获。
之前在做CDN运维的时候,因为业务的特殊性(跨机房,跨ISP,跨区域),把日志集中传输到一个中心来做qos的分析不太现实,因此采用的方法是每5分钟对Nginx日志进行切割,然后通过Python程序计算http code的分布,并通过Zabbix来实现单台机器Nginx qos的监控,配合对Zabbix数据库的Lastvalue进行聚合,则可以监控整个CDN的流量,qos数据等,这样一般发现问题的延迟就在5分钟左右(cdn的qos敏感性不是很强),配合rsync+hadoop+hive来计算nginx的日志,也可以得到更加详细的各个维度的分析(离线数据分析),下面贴下Nginx日志使用的分析脚本:
先贴下zabbix聚合脚本:
#!/usr/bin/python #to get webcdn totaol statistics # -*- coding: utf8 -*- import MySQLdb import sys import os def get_total_value(sql): db = MySQLdb.connect(host='xxxx',user='xxxx',passwd='xxxx',db='xxxx') cursor = db.cursor() cursor.execute(sql) try: result = cursor.fetchone()[0] except: result = 0 cursor.close() db.close() return result if __name__ == '__main__': sql = '' if sys.argv[1] == "network_traffic": sql = "select round(sum(lastvalue)/(1024*1024),4) from hosts a, items b where key_ in ( 'net.if.out[eth2,bytes]','net.if.out[eth0,bytes]') and lower(host) like '%-cdn-cache%' and a.hostid = b.hostid" elif sys.argv[1] == "nginx_traffic": sql = "select sum(lastvalue) from hosts a, items b where key_ = 'log_webcdn_getvalue[traffic]' and lower(host) like '%cdn-cache%' and a.hostid = b.hostid" elif sys.argv[1] == "2xxand3xx": sql = "select sum(lastvalue) from hosts a, items b where key_ in ( 'log_webcdn_getvalue[200]','log_webcdn_getvalue[300]') and lower(host) like '%-cdn-cache%' and a.hostid = b.hostid" elif sys.argv[1] == "4xxand5xx": sql = "select sum(lastvalue) from hosts a, items b where key_ in ( 'log_webcdn_getvalue[four]','log_webcdn_getvalue[five]') and lower(host) like '%-cdn-cache%' and a.hostid = b.hostid" elif sys.argv[1] == "network_ss": sql = "select sum(lastvalue) from hosts a, items b where key_ = 'network_conn' and lower(host) like '%-cdn-cache%' and a.hostid = b.hostid" else: sys.exit(0) # print sql value = get_total_value(sql) print value
然后是单台的分析脚本:
#!/usr/bin/python #coding=utf-8 from __future__ import division import subprocess, signal,string import codecs import re import os import time, datetime import sys def show_usage(): print """ python nginx_log_wedcdn.py result_key result_key could be: average_bodysize, response_time, sum_count, count_success, four, 403, 404, 499, five, 500, 502, 503, 200, 300, requests_second response_time_source, percentage_time_1, percentage_time_3, all """ def runCmd(command, timeout = 10): start = datetime.datetime.now() process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True) while process.poll() is None: time.sleep(0.2) now = datetime.datetime.now() if (now - start).seconds > timeout: os.kill(process.pid, signal.SIGKILL) os.waitpid(-1, os.WNOHANG) return None return process.stdout.readlines() def get_old_filename(): t = datetime.datetime.now() + datetime.timedelta(minutes = -5) a = t.strftime('%Y-%m-%d-%H') b = t.strftime('%M') b = int(b)//5*5 if b < 10: c = "0" + str(b) else: c = str(b) d = "/log/nginx/old/" + a + "-%s.log.gz" % c #print d return d def get_new_filename(): t = datetime.datetime.now() + datetime.timedelta(minutes = -5) a = t.strftime('%Y-%m-%d-%H') b = t.strftime('%M') b = int(b)//5*5 if b < 10: c = "0" + str(b) else: c = str(b) d = "/log/nginx/old/" + a + "-%s.log" % c #print d return d def get_new2_filename(): t = datetime.datetime.now() + datetime.timedelta(minutes = -5) a = t.strftime('%Y-%m-%d-%H') b = t.strftime('%M') b = int(b)//5*5 if b < 10: c = "0" + str(b) else: c = str(b) d = "/log/nginx/new/" + a + "-%s.log" % c #print d return d def average_flow(): flow = 0 flow1 = 0 flow_ppsucai = 0 flow_asimgs = 0 flow_static9 = 0 traffic = 0.0 traffic1 = 0.0 count = 0 count_sucai = 0 count_sucai_100 = 0 count_sucai_30_100 = 0 count_sucai_30 = 0 count_asimgs = 0 count_asimgs_100 = 0 count_asimgs_30_100 = 0 count_asimgs_30 = 0 count_static9 = 0 count_static9_100 = 0 count_static9_30_100 = 0 count_static9_30 = 0 sum_time = 0.0 sum_ppsucai_time = 0.0 sum_asimgs_time = 0.0 sum_static9_time = 0.0 sum_time_source = 0.0 count_200 = 0 count_300 = 0 count_success = 0 count_200_backup = 0 count_not_200_backup = 0 id_list_200 = [200,206] id_list_300 = [300,301,302,303,304,305,306,307] id_list_success = [200,206,300,301,302,303,304,305,306,307] data_byte = 0 elapsed = 0.0 response_time = 0.0 response_time_source = 0.0 requests_second = 0.0 requests_second_sucai = 0.0 requests_second_asimgs = 0.0 list_time_1 = [] list_time_3 = [] list_ip_403 = [] list_ip_404 = [] list_ip_415 = [] list_ip_499 = [] list_ip_500 = [] list_ip_502 = [] list_ip_503 = [] server_list = ['"127.0.0.1:8080"','"127.0.0.1:8081"','"-"'] file_name = get_old_filename() if os.path.isfile("%s" % file_name): Writelog(file_name) i = os.popen("/bin/zcat %s" % file_name).readlines() #i = gzip.GzipFile("%s" % file_name).readlines() else: file_name = get_new_filename() if os.path.isfile("%s" % file_name): Writelog(file_name) i = os.popen("/bin/cat %s" % file_name).readlines() else: #time.sleep(15) file_name = get_new2_filename() if os.path.isfile("%s" % file_name): Writelog(file_name) i = os.popen("/bin/cat %s" % file_name).readlines() else: os.popen("rm -f /tmp/exist.txt") sys.exit(1) for line in i: count += 1 try: domain_name = line.split()[1] except: pass try: web_code = int(line.split()[8]) except: web_code = 888 try: IP = str(line.split()[0]) except: pass try: data_byte = int(line.split()[9]) #print "data", data_byte except: data_byte = 0.0001 try: elapsed = float(line.split()[-1].strip('"')) if elapsed == 0.000: elapsed = 0.0001 except: elapsed = 0.0001 try: time_source = float(line.split()[-4].strip('"')) except: time_source = 0.0 try: backup_server = str(line.split()[-3]) except: pass flow1 += data_byte if web_code in id_list_success: flow += data_byte sum_time_source += time_source if domain_name != "ppsucai.pptv.com": sum_time += elapsed else: #print domain_name sum_time += 0.000 if web_code in id_list_200: #print web_code count_200 += 1 if backup_server not in server_list: #print web_code, backup_server count_200_backup += 1 elif web_code == 200 and date_byte == 0: #print line.split()[3].lstrip("[") WriteURLInfo(line.split()[3].lstrip("[")) WriteURLInfo("\t") WriteURLInfo(line.split()[10]) WriteURLInfo("\n") elif web_code in id_list_300: count_300 += 1 elif web_code == 403 and IP not in list_ip_403: list_ip_403.append(IP) #print "this is the sum 403 count:", IP, len(list_ip_403) elif web_code == 404 and IP not in list_ip_404: list_ip_404.append(IP) #print "this is the sum 404 count:", IP, len(list_ip_404) elif web_code == 415 and IP not in list_ip_415: list_ip_415.append(IP) #print "this is the sum 415 count:", IP, len(list_ip_415) elif web_code == 499 and IP not in list_ip_499: list_ip_499.append(IP) #print "this is the sum 499 count:", IP, len(list_ip_499) elif web_code == 500 and IP not in list_ip_500: list_ip_500.append(IP) #print "this is the sum 500 count:", IP, len(list_ip_500) elif web_code == 502 and IP not in list_ip_502: list_ip_502.append(IP) #print "this is the sum 502 count:", IP, len(list_ip_502) elif web_code == 503 and IP not in list_ip_503: list_ip_503.append(IP) #print "this is the sum 503 count:", IP, len(list_ip_503) if web_code not in id_list_200 and backup_server not in server_list: #print web_code, backup_server count_not_200_backup += 1 if elapsed > 1.0 and web_code in id_list_success and IP not in list_time_1: list_time_1.append(IP) elif elapsed > 3.0 and web_code in id_list_success and IP not in list_time_3: list_time_3.append(IP) if domain_name == "ppsucai.pptv.com" and web_code in id_list_success: download_speed_sucai = round(data_byte / elapsed / 1024, 2) flow_ppsucai += data_byte sum_ppsucai_time += elapsed count_sucai += 1 if download_speed_sucai >= 100: count_sucai_100 += 1 elif download_speed_sucai < 100 and download_speed_sucai >= 30: count_sucai_30_100 += 1 else: count_sucai_30 += 1 elif domain_name == "asimgs.pplive.cn" and web_code in id_list_success: download_speed_asimgs = round(data_byte / elapsed / 1024, 2) flow_asimgs += data_byte sum_asimgs_time += elapsed count_asimgs += 1 if download_speed_asimgs >= 100: count_asimgs_100 += 1 elif download_speed_asimgs < 100 and download_speed_asimgs >= 30: count_asimgs_30_100 += 1 else: count_asimgs_30 += 1 elif domain_name == "static9.pplive.cn" and web_code in id_list_success: download_speed_static9 = round(data_byte / elapsed / 1024, 2) flow_static9 += data_byte sum_static9_time += elapsed count_static9 += 1 if download_speed_static9 >= 100: count_static9_100 += 1 elif download_speed_static9 < 100 and download_speed_static9 >= 30: count_static9_30_100 += 1 else: count_static9_30 += 1 #else: #break try: traffic = round((flow*1.07*8)/300/1024/1024, 2) #traffic1 = round((flow1*1.07)/300/1024/1024, 2) #print traffic, traffic1 #traffic1 = round(flow/sum_time/1024/1024, 2) count_success = count_200 + count_300 response_time = round(sum_time/count_success, 2) response_time_source = round(sum_time_source/count_success, 2) requests_second = round(count_success/300, 2) if sum_ppsucai_time == 0.0: sum_ppsucai_time = 0.0001 if sum_asimgs_time == 0.0: sum_asimgs_time = 0.0001 #print sum_static9_time if sum_static9_time == 0.0: sum_static9_time = 0.0001 traffic_ppsucai = round(flow_ppsucai/sum_ppsucai_time/1024, 2) traffic_asimgs = round(flow_asimgs/sum_asimgs_time/1024, 2) traffic_static9 = round(flow_static9/sum_static9_time/1024, 2) #print "flow_static:", flow_static9, "traffic_static9", traffic_static9 average_bodysize = round((flow/count_success)/1024, 2) percentage_time_1 = round(len(list_time_1)/count_success*100, 2) percentage_time_3 = round(len(list_time_3)/count_success*100, 2) if count_sucai == 0: count_sucai = 0.0001 percentage_sucai_100 = round(count_sucai_100/count_sucai*100, 2) percentage_sucai_30_100 = round(count_sucai_30_100/count_sucai*100, 2) percentage_sucai_30 = round(count_sucai_30/count_sucai*100, 2) if count_asimgs == 0: count_asimgs = 0.0001 percentage_asimgs_100 = round(count_asimgs_100/count_asimgs*100, 2) percentage_asimgs_30_100 = round(count_asimgs_30_100/count_asimgs*100, 2) percentage_asimgs_30 = round(count_asimgs_30/count_asimgs*100, 2) #print count_static9 if count_static9 == 0: count_static9 = 0.0001 percentage_static9_100 = round(count_static9_100/count_static9*100, 2) #print count_static9_100, "100", percentage_static9_100 percentage_static9_30_100 = round(count_static9_30_100/count_static9*100, 2) #print count_static9_30_100, "30-100", percentage_static9_30_100 percentage_static9_30 = round(count_static9_30/count_static9*100, 2) #print count_static9_30, "30", percentage_static9_30 requests_second_sucai = round(count_sucai/300, 2) requests_second_asimgs = round(count_asimgs/300, 2) requests_second_static9 = round(count_static9/300, 2) #print requests_second_static9 #print count, "this is the count of 2xx_backup:", count_200_backup,"%", round(count_200_backup/count, 4),"this is the count of !2xx_backup:", count_not_200_backup, round(count_not_200_backup/count, 4) percentage_200_backup = round(count_200_backup/count*100, 2) percentage_not_200_backup = round(count_not_200_backup/count*100, 2) return average_bodysize, response_time, count, count_success, len(list_ip_403), len(list_ip_404), len(list_ip_499), len(list_ip_500), len(list_ip_502), len(list_ip_503), count_200, count_300, requests_second, response_time_source, len(list_time_1), len(list_time_3), percentage_time_1, percentage_time_3,count_sucai,percentage_sucai_100, percentage_sucai_30_100, percentage_sucai_30, requests_second_sucai, count_asimgs, percentage_asimgs_100, percentage_asimgs_30_100, percentage_asimgs_30, requests_second_asimgs, traffic_ppsucai, traffic_asimgs, traffic, traffic_static9, count_static9, percentage_static9_100, percentage_static9_30_100, percentage_static9_30, requests_second_static9, percentage_200_backup, percentage_not_200_backup, len(list_ip_415) except: return 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 def log_files(pwd): log_file_list = [] files = os.popen("ls %s" % pwd).readlines() for x in files: if x.strip().endswith("log"): log_file_list.append(x.strip()) return log_file_list def result_dic(): list = average_flow() #print list # print list result = {} result['average_bodysize'] = list[0] result['response_time'] = list[1] result['sum_count'] = list[2] result['count_success'] = list[3] result['four'] = list[4] + list[5] + list[6] + list[39] # print 'four','=','%s' % list[4],'+','%s' % list[5],'+','%s' % list[6],'+','%s' % list[39], result['four'] result['403'] = list[4] # print '403', result['403'] result['404'] = list[5] # print '404', result['404'] result['499'] = list[6] # print '499', result['499'] result['415'] = list[39] # print '415', result['415'] result['five'] = list[7] + list[8] + list[9] result['500'] = list[7] result['502'] = list[8] result['503'] = list[9] result['200'] = list[10] result['300'] = list[11] result['requests_second'] = list[12] result['response_time_source'] = list[13] result['percentage_time_1'] = list[16] result['percentage_time_3'] = list[17] result['count_sucai'] = list[18] result['percentage_sucai_100'] = list[19] result['percentage_sucai_30_100'] = list[20] result['percentage_sucai_30'] = list[21] result['requests_second_sucai'] = list[22] result['count_asimgs'] = list[23] result['percentage_asimgs_100'] = list[24] result['percentage_asimgs_30_100'] = list[25] result['percentage_asimgs_30'] = list[26] result['requests_second_asimgs'] = list[27] result['traffic_ppsucai'] = list[28] result['traffic_asimgs'] = list[29] result['traffic'] = list[30] result['traffic_static9'] = list[31] result['count_static9'] = list[32] result['percentage_static9_100'] = list[33] result['percentage_static9_30_100'] = list[34] result['percentage_static9_30'] = list[35] result['requests_second_static9'] = list[36] result['percentage_200_backup'] = list[37] result['percentage_not_200_backup'] = list[38] result['all'] = list return result def Writelog(msg): o = open("/log/nginx/qos_result_new"+".log","aw") o.write(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + ":" + msg + "\n") o.close() def WriteTmpInfo(msg): o = open("/tmp/webcdnqos_result"+".txt","aw+") o.write(msg+"\n") o.close() def WriteURLInfo(msg): today = datetime.date.today() o = open("/tmp/webcdnqos_url_%s" % today.strftime('%Y-%m-%d') + ".log","aw") # o.write(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + " " +msg+"\n") o.write(msg) o.close() if __name__ == "__main__": if len(sys.argv) < 2: show_usage() os.popen("rm -f /tmp/exist.txt") sys.exit(1) else: if os.path.isfile("/tmp/exist.txt"): sys.exit(1) else: os.popen("echo 'hello' > /tmp/exist.txt") result_key = sys.argv[1] status = result_dic() os.popen(">/tmp/webcdnqos_result.txt") print status[result_key] Writelog(str(status[result_key])) for i in status.keys(): WriteTmpInfo(str(i)+"="+str(status[i])) os.popen("rm -f /tmp/exist.txt")
看完上述内容,你们对Nginx Httpcode的分析脚本是什么有进一步的了解吗?如果还想了解更多知识或者相关内容,请关注亿速云行业资讯频道,感谢大家的支持。
免责声明:本站发布的内容(图片、视频和文字)以原创、转载和分享为主,文章观点不代表本网站立场,如果涉及侵权请联系站长邮箱:is@yisu.com进行举报,并提供相关证据,一经查实,将立刻删除涉嫌侵权内容。