设计一个基于flask的高并发高可用的查询ip的http服务

结构设计

基础架构为flask+gunicorn+负载均衡，负载均衡分为阿里云硬件负载均衡服务和软负载nginx。gunicorn使用supervisor进行管理。

使用nginx软件负载结构图

使用阿里云硬件负载均衡服务结构图

因为flask app需要在内存中保存ip树以及国家、省份、城市相关的字典，因此占用内存较高。gunicorn的1个worker需要占用300M内存，nginx的4个worker内存占用较小（不到100M），因此占用1.3G的内存（即需要一个2G内存的服务器）。当gunicorn任意一个节点挂断或者升级时，另外一个节点仍然在使用，不会影响整体服务

ip数据库

IP库(也叫IP地址数据库)，是由专业技术人员经过长时间通过多种技术手段收集而来的，并且长期有专业人员进行更新、维护、补充。

ip数据库解析查询代码

基于二叉查找树实现

import struct
from socket import inet_aton, inet_ntoa
import os
import sys

sys.setrecursionlimit(1000000)

_unpack_V = lambda b: struct.unpack("L", b)
_unpack_C = lambda b: struct.unpack("B", b)


class IpTree:
    def __init__(self):
        self.ip_dict = {}
        self.country_codes = {}
        self.china_province_codes = {}
        self.china_city_codes = {}

    def load_country_codes(self, file_name):
        try:
            path = os.path.abspath(file_name)
            with open(path, "rb") as f:
                for line in f.readlines():
                    data = line.split('\t')
                    self.country_codes[data[0]] = data[1]
                    # print self.country_codes
        except Exception as ex:
            print "cannot open file %s: %s" % (file, ex)
            print ex.message
            exit(0)

    def load_china_province_codes(self, file_name):
        try:
            path = os.path.abspath(file_name)
            with open(path, "rb") as f:
                for line in f.readlines():
                    data = line.split('\t')
                    provinces = data[2].split('\r')
                    self.china_province_codes[provinces[0]] = data[0]
                    # print self.china_province_codes
        except Exception as ex:
            print "cannot open file %s: %s" % (file, ex)
            print ex.message
            exit(0)

    def load_china_city_codes(self, file_name):
        try:
            path = os.path.abspath(file_name)
            with open(path, "rb") as f:
                for line in f.readlines():
                    data = line.split('\t')
                    cities = data[3].split('\r')
                    self.china_city_codes[cities[0]] = data[0]
        except Exception as ex:
            print "cannot open file %s: %s" % (file, ex)
            print ex.message
            exit(0)

    def loadfile(self, file_name):
        try:
            ipdot0 = 254
            path = os.path.abspath(file_name)
            with open(path, "rb") as f:
                local_binary0 = f.read()
                local_offset, = _unpack_N(local_binary0[:4])
                local_binary = local_binary0[4:local_offset]
                # 256 nodes
                while ipdot0 >= 0:
                    middle_ip = None
                    middle_content = None
                    lis = []
                    # offset
                    begin_offset = ipdot0 * 4
                    end_offset = (ipdot0 + 1) * 4
                    # index
                    start_index, = _unpack_V(local_binary[begin_offset:begin_offset + 4])
                    start_index = start_index * 8 + 1024
                    end_index, = _unpack_V(local_binary[end_offset:end_offset + 4])
                    end_index = end_index * 8 + 1024
                    while start_index < end_index:
                        content_offset, = _unpack_V(local_binary[start_index + 4: start_index + 7] +
                                                    chr(0).encode('utf-8'))
                        content_length, = _unpack_C(local_binary[start_index + 7])
                        content_offset = local_offset + content_offset - 1024
                        content = local_binary0[content_offset:content_offset + content_length]
                        if middle_content != content and middle_content is not None:
                            contents = middle_content.split('\t')
                            lis.append((middle_ip, (contents[0], self.lookup_country_code(contents[0]),
                                                    contents[1], self.lookup_china_province_code(contents[1]),
                                                    contents[2], self.lookup_china_city_code(contents[2]),
                                                    contents[3], contents[4])))
                        middle_content, = content,
                        middle_ip = inet_ntoa(local_binary[s