sphinx增量索引
首先建立一个计数表,保存数据表的最新记录ID
CREATE TABLE `sph_counter` (
`id` int(11) unsigned NOT NULL,
`max_id` int(11) unsigned NOT NULL,
PRIMARY KEY (`id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8 COMMENT='sphinx增量表最大记录数';
#定义主索引源
source test
{
type = mysql
sql_host = localhost
sql_user = root
sql_pass = 8888
sql_db = test
sql_port = 3306
sql_query_pre = SET NAMES utf8
sql_query_pre = REPLACE INTO sph_counter SELECT 1, MAX(id) FROM test where status=1 #取最大记录数
sql_query = select id from test where status = 1
sql_query_info = select * from test where id = $id
}
#增量索引数据源定义
source test_delta : test
{
sql_query_pre = SET NAMES utf8
sql_query = select * from test where id>=(select max_id from sph_counter where id=1) and status = 1
sql_query_info = select * from test where id = $id
}
#定义主索引
index test
{
source = test #对应的source名称
path = /usr/local/sphinx/var/data/test #请修改为实际使用的绝对路径,例如:/usr/local/coreseek/var/...
docinfo = extern
mlock = 0
morphology = none
min_word_len = 2
html_strip = 1
#中文分词配置,详情请查看:http://www.coreseek.cn/products-install/coreseek_mmseg/
charset_dictpath = /usr/local/mmseg/etc/ #BSD、Linux环境下设置,/符号结尾
#charset_dictpath = etc/ #Windows环境下设置,/符号结尾,最好给出绝对路径,例如:C:/usr/local/coreseek/etc/...
charset_type = zh_cn.utf-8
}
#定义增量索引
index test_delta:test
{
source = test_delta #对应的source名称
path = /usr/local/sphinx/var/data/test_delta #请修改为实际使用的绝对路径,例如:/usr/local/coreseek/var/...
docinfo = extern
mlock = 0
morphology = none
min_word_len = 2
html_strip = 1
#中文分词配置,详情请查看:http://www.coreseek.cn/products-install/coreseek_mmseg/
charset_dictpath = /usr/local/mmseg/etc/ #BSD、Linux环境下设置,/符号结尾
#charset_dictpath = etc/ #Windows环境下设置,/符号结尾,最好给出绝对路径,例如:C:/usr/local/coreseek/etc/...
charset_type = zh_cn.utf-8
}
#全局index定义
indexer
{
mem_limit = 128M
}
#searchd服务定义
searchd
{
listen = 9312
read_timeout = 5
max_children = 30
max_matches = 1000
seamless_rotate = 0
preopen_indexes = 0
unlink_old = 1
pid_file = /usr/local/sphinx/var/log/searchd_mysql.pid #请修改为实际使用的绝对路径,例如:/usr/local/coreseek/var/...
log = /usr/local/sphinx/var/log/searchd_mysql.log #请修改为实际使用的绝对路径,例如:/usr/local/coreseek/var/...
query_log = /usr/local/sphinx/var/log/query_mysql.log #请修改为实际使用的绝对路径,例如:/usr/local/coreseek/var/...
binlog_path = #关闭binlog日志
}
保存配置文件后退出,先停止searchd进程再启动,然后重新生成索引。
停止进程
/usr/local/sphinx/bin/searchd -c /usr/local/sphinx/etc/csft.conf --stop
启动进程
/usr/local/sphinx/bin/searchd -c /usr/local/sphinx/etc/csft.conf
重新生成所有索引
/usr/local/sphinx/bin/indexer -c /usr/local/sphinx/etc/csft.conf --all --rotate
增量索引
/usr/local/sphinx/bin/indexer -c /usr/local/sphinx/etc/csft.conf test_delta --rotate
合并索引
/usr/local/sphinx/bin/indexer -c /usr/local/sphinx/etc/csft.conf --merge test test_delta --rotate
如果合并索引时出现下面问题:
FATAL: failed to merge index 'test_delta' into index 'test': source index preload failed: failed to open /usr/local/sphinx/var/data/test_delta.sph: No such file or directory
停止searchd进程,然后重新启动searchd进程。
增量索引可以放在crontab里根据需要设置几分钟运行一次,然后执行索引合并,至于主索引重建可以选择在访问量不大或者半夜运行。
##每5分钟运行增量索引
*/5 * * * /usr/local/sphinx/bin/indexer -c /usr/local/sphinx/etc/csft.conf test_delta --rotate > /dev/null 2>&1
##每10分钟执行一次增量索引合并
*/10 * * * /usr/local/sphinx/bin/indexer -c /usr/local/sphinx/etc/csft.conf --merge test test_delta --rotate
##凌晨0点5分重新建立主索引
5 0 * * * /usr/local/sphinx/bin/indexer -c /usr/local/sphinx/etc/csft.conf --all --rotate > /dev/null 2>&1