应用场景

这里列举几个应用场景，下文会针对这几个场景并结合代码进行分析。

1. proxy_pass + upstream

    upstream foo.example.com {

        server 127.0.0.1:8001;

    }

    server {

        listen       80;

        server_name  localhost;

        location /foo {

            proxy_pass http://foo.example.com;

        }

    }

访问http://localhost/foo，proxy模块会将请求转发到127.0.0.1的8001端口上。

1. 只有proxy_pass，没有upstream与resolver

    server {

        listen       80;

        server_name  localhost;

        location /foo {

            proxy_pass http://foo.example.com;

        }

    }

实际上是隐式创建了upstream，upstream名字就是foo.example.com。upstream模块利用本机设置的DNS服务器（或/etc/hosts），将foo.example.com解析成IP，访问http://localhost/foo，proxy模块会将请求转发到解析后的IP上。

如果本机未设置DNS服务器，或者DNS服务器无法解析域名，则nginx启动时会报类似如下错误：

nginx: [emerg] host not found in upstream "foo.example.com" in /path/nginx/conf/nginx.conf:110

1. proxy_pass + resolver（变量设置域名）

    server {

        listen       80;

        server_name  localhost;

        resolver 114.114.114.114;

        location /foo {

            set $foo foo.example.com;

            proxy_pass http://$foo;

        }

    }

访问http://localhost/foo，nginx会动态利用resolver设置的DNS服务器（本机设置的DNS服务器或/etc/hosts无效），将域名解析成IP，proxy模块会将请求转发到解析后的IP上。

1. proxy_pass + upstream（显式） + resolver（变量设置域名）

    upstream foo.example.com {

        server 127.0.0.1:8001;

    }

    server {

        listen       80;

        server_name  localhost;

        resolver 114.114.114.114;

        location /foo {

            set $foo foo.example.com;

            proxy_pass http://$foo;

        }

    }

访问http://localhost/foo时，upstream模块会优先查找是否有定义upstream后端服务器，如果有定义则直接利用，不再走DNS解析。所以proxy模块会将请求转发到127.0.0.1的8001端口上。

1. proxy_pass + upstream（隐式） + resolver（变量设置域名）

    server {

        listen       80;

        server_name  localhost;

        resolver 114.114.114.114;

        location /foo {

            set $foo foo.example.com;

            proxy_pass http://$foo;

        }

        location /foo2 {

            proxy_pass http://foo.example.com;

        }

    }

location /foo2实际上是隐式定义了upstream foo.example.com，并由本地DNS服务器进行了域名解析，访问http://localhost/foo时，upstream模块会优先查找upstream，即隐式定义的foo.example.com，proxy模块会将请求转发到解析后的IP上。

1. proxy_pass + resolver（不用变量设置域名）

    server {

        listen       80;

        server_name  localhost;

        resolver 114.114.114.114;

        location /foo {

            proxy_pass http://foo.example.com;

        }

    }

不使用变量设置域名，则resolver的设置不起作用，此时相当于场景2，只有proxy_pass的场景。

1. proxy_pass + upstream + resolver（不用变量设置域名）

    upstream foo.example.com {

        server 127.0.0.1:8001;

    }

    server {

        listen       80;

        server_name  localhost;

        resolver 114.114.114.114;

        location /foo {

            proxy_pass http://foo.example.com;

        }

    }

不使用变量设置域名，则resolver的设置不起作用，此时相当于场景1 proxy_pass + upstream。

1. proxy_pass 直接指定IP加端口号

    server {

        listen       80;

        server_name  localhost;

        location /foo {

            proxy_pass http://127.0.0.1:8001/;

        }

    }

实际上是隐式创建了upstream，proxy_pass会将请求转发到127.0.0.1的8001端口上。

主要代码

解析proxy_pass指令的代码：

static char *

ngx_http_proxy_pass(ngx_conf_t *cf, ngx_command_t *cmd, void *conf)

{

    ngx_http_proxy_loc_conf_t *plcf = conf;

    size_t                      add;

    u_short                     port;

    ngx_str_t                  *value, *url;

    ngx_url_t                   u;

    ngx_uint_t                  n;

    ngx_http_core_loc_conf_t   *clcf;

    ngx_http_script_compile_t   sc;

    if (plcf->upstream.upstream || plcf->proxy_lengths) {

        return "is duplicate";

    }

    clcf = ngx_http_conf_get_module_loc_conf(cf, ngx_http_core_module);

    clcf->handler = ngx_http_proxy_handler;

    if (clcf->name.data[clcf->name.len - 1] == '/') {

        clcf->auto_redirect = 1;

    }

    value = cf->args->elts;

    url = &value[1];

    /* 查找指令中$符号的位置，判断是否使用了变量 */

    n = ngx_http_script_variables_count(url);

    if (n) {

        /* 使用变量设置域名 */

        ngx_memzero(&sc, sizeof(ngx_http_script_compile_t));

        sc.cf = cf;

        sc.source = url;

        sc.lengths = &plcf->proxy_lengths;

        sc.values = &plcf->proxy_values;

        sc.variables = n;

        sc.complete_lengths = 1;

        sc.complete_values = 1;

        if (ngx_http_script_compile(&sc) != NGX_OK) {

            return NGX_CONF_ERROR;

        }

#if (NGX_HTTP_SSL)

        plcf->ssl = 1;

#endif

        return NGX_CONF_OK;

    }

    if (ngx_strncasecmp(url->data, (u_char *) "http://", 7) == 0) {

        add = 7;

        port = 80;

    } else if (ngx_strncasecmp(url->data, (u_char *) "https://", 8) == 0) {

#if (NGX_HTTP_SSL)

        plcf->ssl = 1;

        add = 8;

        port = 443;

#else

        ngx_conf_log_error(NGX_LOG_EMERG, cf, 0,

                           "https protocol requires SSL support");

        return NGX_CONF_ERROR;

#endif

    } else {

        ngx_conf_log_error(NGX_LOG_EMERG, cf, 0, "invalid URL prefix");

        return NGX_CONF_ERROR;

    }

    ngx_memzero(&u, sizeof(ngx_url_t));

    u.url.len = url->len - add;

    u.url.data = url->data + add;

    u.default_port = port;

    u.uri_part = 1;

    u.no_resolve = 1;

    plcf->upstream.upstream = ngx_http_upstream_add(cf, &u, 0);

    if (plcf->upstream.upstream == NULL) {

        return NGX_CONF_ERROR;

    }

    plcf->vars.schema.len = add;

    plcf->vars.schema.data = url->data;

    plcf->vars.key_start = plcf->vars.schema;

    ngx_http_proxy_set_vars(&u, &plcf->vars);

    plcf->location = clcf->name;

    if (clcf->named

#if (NGX_PCRE)

        || clcf->regex

#endif

        || clcf->noname)

    {

        if (plcf->vars.uri.len) {

            ngx_conf_log_error(NGX_LOG_EMERG, cf, 0,

                               "\"proxy_pass\" cannot have URI part in "

                               "location given by regular expression, "

                               "or inside named location, "

                               "or inside \"if\" statement, "

                               "or inside \"limit_except\" block");

            return NGX_CONF_ERROR;

        }

        plcf->location.len = 0;

    }

    plcf->url = *url;

    return NGX_CONF_OK;

}

upstream定义的后端服务器的处理逻辑，包括显式定义的和隐式定义的。隐式定义，即proxy_pass指定的后端服务器的地址没有显式用upstream定义，nginx内部会定义一个。

ngx_int_t

ngx_http_upstream_init_round_robin(ngx_conf_t *cf,

    ngx_http_upstream_srv_conf_t *us)

{

    ngx_url_t                      u;

    ngx_uint_t                     i, j, n, w;

    ngx_http_upstream_server_t    *server;

    ngx_http_upstream_rr_peer_t   *peer, **peerp;

    ngx_http_upstream_rr_peers_t  *peers, *backup;

    us->peer.init = ngx_http_upstream_init_round_robin_peer;

    /*

     * 使用upstream指令显式定义upstream

     * 或者proxy_pass直接指定IP的场景

     */

    if (us->servers) {

        server = us->servers->elts;

        n = 0;

        w = 0;

        for (i = 0; i < us->servers->nelts; i++) {

            if (server[i].backup) {

                continue;

            }

            n += server[i].naddrs;

            w += server[i].naddrs * server[i].weight;

        }

        if (n == 0) {

            ngx_log_error(NGX_LOG_EMERG, cf->log, 0,

                          "no servers in upstream \"%V\" in %s:%ui",

                          &us->host, us->file_name, us->line);

            return NGX_ERROR;

        }

        peers = ngx_pcalloc(cf->pool, sizeof(ngx_http_upstream_rr_peers_t));

        if (peers == NULL) {

            return NGX_ERROR;

        }

        peer = ngx_pcalloc(cf->pool, sizeof(ngx_http_upstream_rr_peer_t) * n);

        if (peer == NULL) {

            return NGX_ERROR;

        }

        peers->single = (n == 1);

        peers->number = n;

        peers->weighted = (w != n);

        peers->total_weight = w;

        peers->name = &us->host;

        n = 0;

        peerp = &peers->peer;

        for (i = 0; i < us->servers->nelts; i++) {

            /* 设置sockaddr、weight、max_fails、fail_timeout等属性 */

        }

        us->peer.data = peers;

        /* 处理backup servers相关逻辑 */

        return NGX_OK;

    }

    /* 未使用upstream指令，使用proxy_pass隐式定义upstream */

    /* an upstream implicitly defined by proxy_pass, etc. */

    if (us->port == 0) {

        ngx_log_error(NGX_LOG_EMERG, cf->log, 0,

                      "no port in upstream \"%V\" in %s:%ui",

                      &us->host, us->file_name, us->line);

        return NGX_ERROR;

    }

    ngx_memzero(&u, sizeof(ngx_url_t));

    u.host = us->host;

    u.port = us->port;

    if (ngx_inet_resolve_host(cf->pool, &u) != NGX_OK) {

        if (u.err) {

            ngx_log_error(NGX_LOG_EMERG, cf->log, 0,

                          "%s in upstream \"%V\" in %s:%ui",

                          u.err, &us->host, us->file_name, us->line);

        }

        return NGX_ERROR;

    }

    n = u.naddrs;

    peers = ngx_pcalloc(cf->pool, sizeof(ngx_http_upstream_rr_peers_t));

    if (peers == NULL) {

        return NGX_ERROR;

    }

    peer = ngx_pcalloc(cf->pool, sizeof(ngx_http_upstream_rr_peer_t) * n);

    if (peer == NULL) {

        return NGX_ERROR;

    }

    peers->single = (n == 1);

    peers->number = n;

    peers->weighted = 0;

    peers->total_weight = n;

    peers->name = &us->host;

    peerp = &peers->peer;

    for (i = 0; i < u.naddrs; i++) {

        /* 设置sockaddr、weight、max_fails、fail_timeout等属性 */

    }

    us->peer.data = peers;

    /* implicitly defined upstream has no backup servers */

    return NGX_OK;

}

upstream模块初始化请求时的逻辑：

static void

ngx_http_upstream_init_request(ngx_http_request_t *r)

{

    ngx_str_t                      *host;

    ngx_uint_t                      i;

    ngx_resolver_ctx_t             *ctx, temp;

    ngx_http_cleanup_t             *cln;

    ngx_http_upstream_t            *u;

    ngx_http_core_loc_conf_t       *clcf;

    ngx_http_upstream_srv_conf_t   *uscf, **uscfp;

    ngx_http_upstream_main_conf_t  *umcf;

    if (r->aio) {

        return;

    }

    u = r->upstream;

    /* NGX_HTTP_CACHE 等其他处理 */

    cln->handler = ngx_http_upstream_cleanup;

    cln->data = r;

    u->cleanup = &cln->handler;

    if (u->resolved == NULL) {

        /* 如果没有使用resolver设置DNS，直接取upstream的设置 */

        uscf = u->conf->upstream;

    } else {

#if (NGX_HTTP_SSL)

        u->ssl_name = u->resolved->host;

#endif

        host = &u->resolved->host;

        if (u->resolved->sockaddr) {

            if (u->resolved->port == 0

                && u->resolved->sockaddr->sa_family != AF_UNIX)

            {

                ngx_log_error(NGX_LOG_ERR, r->connection->log, 0,

                              "no port in upstream \"%V\"", host);

                ngx_http_upstream_finalize_request(r, u,

                                               NGX_HTTP_INTERNAL_SERVER_ERROR);

                return;

            }

            if (ngx_http_upstream_create_round_robin_peer(r, u->resolved)

                != NGX_OK)

            {

                ngx_http_upstream_finalize_request(r, u,

                                               NGX_HTTP_INTERNAL_SERVER_ERROR);

                return;

            }

            ngx_http_upstream_connect(r, u);

            return;

        }

        umcf = ngx_http_get_module_main_conf(r, ngx_http_upstream_module);

        uscfp = umcf->upstreams.elts;

        /* 在显式/隐式定义的upstream中查找 */

        for (i = 0; i < umcf->upstreams.nelts; i++) {

            uscf = uscfp[i];

            if (uscf->host.len == host->len

                && ((uscf->port == 0 && u->resolved->no_port)

                     || uscf->port == u->resolved->port)

                && ngx_strncasecmp(uscf->host.data, host->data, host->len) == 0)

            {

                goto found;

            }

        }

        if (u->resolved->port == 0) {

            ngx_log_error(NGX_LOG_ERR, r->connection->log, 0,

                          "no port in upstream \"%V\"", host);

            ngx_http_upstream_finalize_request(r, u,

                                               NGX_HTTP_INTERNAL_SERVER_ERROR);

            return;

        }

        temp.name = *host;

        ctx = ngx_resolve_start(clcf->resolver, &temp);

        if (ctx == NULL) {

            ngx_http_upstream_finalize_request(r, u,

                                               NGX_HTTP_INTERNAL_SERVER_ERROR);

            return;

        }

        if (ctx == NGX_NO_RESOLVER) {

            ngx_log_error(NGX_LOG_ERR, r->connection->log, 0,

                          "no resolver defined to resolve %V", host);

            ngx_http_upstream_finalize_request(r, u, NGX_HTTP_BAD_GATEWAY);

            return;

        }

        ctx->name = *host;

        ctx->handler = ngx_http_upstream_resolve_handler;

        ctx->data = r;

        ctx->timeout = clcf->resolver_timeout;

        u->resolved->ctx = ctx;

        if (ngx_resolve_name(ctx) != NGX_OK) {

            u->resolved->ctx = NULL;

            ngx_http_upstream_finalize_request(r, u,

                                               NGX_HTTP_INTERNAL_SERVER_ERROR);

            return;

        }

        return;

    }

found:

    if (uscf == NULL) {

        ngx_log_error(NGX_LOG_ALERT, r->connection->log, 0,

                      "no upstream configuration");

        ngx_http_upstream_finalize_request(r, u,

                                           NGX_HTTP_INTERNAL_SERVER_ERROR);

        return;

    }

#if (NGX_HTTP_SSL)

    u->ssl_name = uscf->host;

#endif

    if (uscf->peer.init(r, uscf) != NGX_OK) {

        ngx_http_upstream_finalize_request(r, u,

                                           NGX_HTTP_INTERNAL_SERVER_ERROR);

        return;

    }

    u->peer.start_time = ngx_current_msec;

    if (u->conf->next_upstream_tries

        && u->peer.tries > u->conf->next_upstream_tries)

    {

        u->peer.tries = u->conf->next_upstream_tries;

    }

    ngx_http_upstream_connect(r, u);

}

详细分析

场景1

解析proxy_pass的函数ngx_http_proxy_pass中，没有找到$符号（即，变量设置域名），走ngx_http_proxy_pass后半部分的处理逻辑。ngx_http_upstream_init_round_robin初始化upstream时，走显式定义upstream的逻辑。proxy_pass转发请求初始化时，ngx_http_upstream_init_request中直接使用upstream中的后端server建立连接。

场景2

ngx_http_upstream_init_round_robin初始化upstream时，走隐式定义upstream的逻辑，会调用ngx_inet_resolve_host对proxy_pass中的域名进行解析，设置upstream。proxy_pass转发请求初始化时，ngx_http_upstream_init_request中直接使用upstream中的设置，也就是利用本地设置的DNS服务器解析出的IP，建立连接。

场景3

解析proxy_pass指令时，找到了$符号，设置ngx_http_script_compile_t，并利用ngx_http_script_compile进行编译，不走后半部分逻辑。配置文件没有显式/隐式定义upstream，所以不会调用ngx_http_upstream_init_round_robin方法。proxy_pass转发请求初始化时，ngx_http_upstream_init_request中发现没有显式也没有隐式定义的upstream，随后调用ngx_resolve_start，对域名进行解析，之后将请求转发过去。

场景4

解析proxy_pass指令时，找到了$符号，设置ngx_http_script_compile_t，并利用ngx_http_script_compile进行编译，不走后半部分逻辑。显式调用了upstream，所以调用ngx_http_upstream_init_round_robin方法中的显式upstream的处理逻辑。proxy_pass转发请求初始化时，ngx_http_upstream_init_request中优先查找upstream，如果找到了，直接将请求转发到upstream中的后端server上。如果upstream中没有找到，则对域名进行解析，然后将请求转发到解析后的IP上。

场景5

基本与场景4相同，不同之处在于调用ngx_http_upstream_init_round_robin方法时，走隐式upstream部分的处理逻辑。

场景6

与场景2相同。

场景7

与场景1相同。

场景8

实际上是隐式创建了upstream，但是因为proxy_pass中指定了IP和端口号，所以ngx_http_upstream_init_round_robin初始化upstream时，us->servers不为空，所以走该函数的上半部分逻辑。与场景1有些类似。

https://www.jianshu.com/p/5caa48664da5