nginx upstream健康检测

自带健康检测module

nginx本身提供有健康检测module ngx_http_upstream_module ,利用自身的module可以实现简单的健康检测

下载nginx模块
wget https://github.com/nginx/nginx/archive/release-1.19.3.tar.gz

解压nginx模块
tar -zxvf release-1.19.3.tar.gz

进入nginx模块目录
cd nginx-release-1.19.3

编译nginx带上ngx_http_upstream_module模块
./configure --add-module=../ngx_http_upstream_module

安装nginx
make && make install

重启nginx
nginx -s reload
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17

第三方健康检测module

第三方插件的module，例如openresty的lua-resty-upstream-healthcheck

http {
    lua_package_path "/path/to/lua-resty-upstream-healthcheck/lib/?.lua;;";

    # sample upstream block:
    upstream foo.com {
        server 127.0.0.1:12354;
        server 127.0.0.1:12355;
        server 127.0.0.1:12356 backup;
    }

    # the size depends on the number of servers in upstream {}:
    lua_shared_dict healthcheck 1m;

    lua_socket_log_errors off;

    init_worker_by_lua_block {
        local hc = require "resty.upstream.healthcheck"

        local ok, err = hc.spawn_checker{
            shm = "healthcheck",  -- defined by "lua_shared_dict"
            upstream = "foo.com", -- defined by "upstream"
            type = "http", -- support "http" and "https"

            http_req = "GET /status HTTP/1.0\r\nHost: foo.com\r\n\r\n",
                    -- raw HTTP request for checking

            port = nil,  -- the check port, it can be different than the original backend server port, default means the same as the original backend server
            interval = 2000,  -- run the check cycle every 2 sec
            timeout = 1000,   -- 1 sec is the timeout for network operations
            fall = 3,  -- # of successive failures before turning a peer down
            rise = 2,  -- # of successive successes before turning a peer up
            valid_statuses = {200, 302},  -- a list valid HTTP status code
            concurrency = 10,  -- concurrency level for test requests
            -- ssl_verify = true, -- https type only, verify ssl certificate or not, default true
            -- host = foo.com, -- https type only, host name in ssl handshake, default nil
        }
        if not ok then
            ngx.log(ngx.ERR, "failed to spawn health checker: ", err)
            return
        end

        -- Just call hc.spawn_checker() for more times here if you have
        -- more upstream groups to monitor. One call for one upstream group.
        -- They can all share the same shm zone without conflicts but they
        -- need a bigger shm zone for obvious reasons.
    }

    server {
        ...

        # status page for all the peers:
        location = /status {
            access_log off;
            allow 127.0.0.1;
            deny all;

            default_type text/plain;
            content_by_lua_block {
                local hc = require "resty.upstream.healthcheck"
                ngx.say("Nginx Worker PID: ", ngx.worker.pid())
                ngx.print(hc.status_page())
            }
        }

	# status page for all the peers (prometheus format):
        location = /metrics {
            access_log off;
            default_type text/plain;
            content_by_lua_block {
                local hc = require "resty.upstream.healthcheck"
                st , err = hc.prometheus_status_page()
                if not st then
                    ngx.say(err)
                    return
                end
                ngx.print(st)
            }
        }
    }
}
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80