当我们需要优化MySQL查询时，第一想到的是开启慢日志，慢日志可以看到执行消耗超过一定时间的SQL语句和未使用索引的SQL。但如果我们想分析所有SQL查询的分布，即哪类SQL查询次数最多的时候，我们可以开启general log来统计。
mysql> show variables like '%general%';
+——————+————————————-+
| Variable_name | Value |
+——————+————————————-+
| general_log | OFF |
| general_log_file | /usr/local/mysql/data/localhost.log |
+——————+————————————-+
mysql> set global general_log = "ON";
#!/usr/bin/python
# sort and count mysql general log
# Author: Jason
# Url: www.centos.bz
# Email: admin#centos.bz
# Created: UTC 2015-02-15 17:51:53
import re
import sys
import os
if len(sys.argv) == 2:
logPath = sys.argv[1]
if not os.path.exists(logPath):
print ("file " + logPath + " does not exists.")
sys.exit(1)
else:
print ("Usage: " + sys.argv[0] + " logPath")
sys.exit(1)
logFo = open(logPath)
match = 0
for line in logFo:
line = re.sub(r"\n","",line)
if match == 0:
# match line begin with numbers
lineMatch = re.match(r"\s+[0-9]+\s+.*",line,flags=re.I)
if lineMatch:
lineTmp = lineMatch.group(0)
match = match + 1
continue
elif match == 1:
# match line begin with numbers
lineMatch = re.match(r"\s+[0-9]+\s+.*",line,flags=re.I)
if lineMatch:
# match only query
lineMatchQuery = re.match(r".*Query\s+(.*)",lineTmp,flags=re.I)
if lineMatchQuery:
lineTmp = lineMatchQuery.group(1)
# remove extra space
lineTmp = re.sub(r"\s+", " ",lineTmp)
# replace values (value) to values (x)
lineTmp = re.sub(r"values\s*\(.*?\)", "values (x)",lineTmp,flags=re.I)
# replace filed = 'value' to filed = 'x'
lineTmp = re.sub(r"(=|>|<|>=|<=)\s*('|\").*?\2","\\1 'x'",lineTmp)
# replace filed = value to filed = x
lineTmp = re.sub(r"(=|>|<|>=|<=)\s*[0-9]+","\\1 x",lineTmp)
# replace like 'value' to like 'x'
lineTmp = re.sub(r"like\s+('|\").*?\1","like 'x'",lineTmp,flags=re.I)
# replace in (value) to in (x)
lineTmp = re.sub(r"in\s+\(.*?\)","in (x)",lineTmp,flags=re.I)
# replace limit x,y to limit
lineTmp = re.sub(r"limit.*","limit",lineTmp,flags=re.I)
print (lineTmp)
match = 1
lineTmp = lineMatch.group(0)
else:
lineTmp += line
match = 1
logFo.close()使用方法：
analysis-general-log.py general.log | sort | uniq -c | sort -nr
该python脚本使用与python2.7以上环境
另外有需要云服务器可以了解下创新互联cdcxhl.cn，海内外云服务器15元起步，三天无理由+7*72小时售后在线，公司持有idc许可证，提供“云服务器、裸金属服务器、高防服务器、香港服务器、美国服务器、虚拟主机、免备案服务器”等云主机租用服务以及企业上云的综合解决方案，具有“安全稳定、简单易用、服务可用性高、性价比高”等特点与优势，专为企业上云打造定制，能够满足用户丰富、多元化的应用场景需求。