nginx的请求接收流程（二）

在ngx_http_process_request_line函数中，解析完请求行之后，如果请求行的uri里面包含了域名部分，则将其保持在请求结构的headers_in成员的server字段，headers_in用来保存所有请求头，它的类型为ngx_http_headers_in_t：

typedef struct {
ngx_list_t headers;
ngx_table_elt_t *host;
ngx_table_elt_t *connection;
ngx_table_elt_t *if_modified_since;
ngx_table_elt_t *if_unmodified_since;
ngx_table_elt_t *user_agent;
ngx_table_elt_t *referer;
ngx_table_elt_t *content_length;
ngx_table_elt_t *content_type;
ngx_table_elt_t *range;
ngx_table_elt_t *if_range;
ngx_table_elt_t *transfer_encoding;
ngx_table_elt_t *expect;
#if (NGX_HTTP_GZIP)
ngx_table_elt_t *accept_encoding;
ngx_table_elt_t *via;
#endif
ngx_table_elt_t *authorization;
ngx_table_elt_t *keep_alive;
#if (NGX_HTTP_PROXY || NGX_HTTP_REALIP || NGX_HTTP_GEO)
ngx_table_elt_t *x_forwarded_for;
#endif
#if (NGX_HTTP_REALIP)
ngx_table_elt_t *x_real_ip;
#endif
#if (NGX_HTTP_HEADERS)
ngx_table_elt_t *accept;
ngx_table_elt_t *accept_language;
#endif
#if (NGX_HTTP_DAV)
ngx_table_elt_t *depth;
ngx_table_elt_t *destination;
ngx_table_elt_t *overwrite;
ngx_table_elt_t *date;
#endif
ngx_str_t user;
ngx_str_t passwd;
ngx_array_t cookies;
ngx_str_t server;
off_t content_length_n;
time_t keep_alive_n;
unsigned connection_type:2;
unsigned msie:1;
unsigned msie6:1;
unsigned opera:1;
unsigned gecko:1;
unsigned chrome:1;
unsigned safari:1;
unsigned konqueror:1;
} ngx_http_headers_in_t;

typedef struct {
    ngx_list_t                        headers;

    ngx_table_elt_t                  *host;
    ngx_table_elt_t                  *connection;
    ngx_table_elt_t                  *if_modified_since;
    ngx_table_elt_t                  *if_unmodified_since;
    ngx_table_elt_t                  *user_agent;
    ngx_table_elt_t                  *referer;
    ngx_table_elt_t                  *content_length;
    ngx_table_elt_t                  *content_type;

    ngx_table_elt_t                  *range;
    ngx_table_elt_t                  *if_range;

    ngx_table_elt_t                  *transfer_encoding;
    ngx_table_elt_t                  *expect;

#if (NGX_HTTP_GZIP)
    ngx_table_elt_t                  *accept_encoding;
    ngx_table_elt_t                  *via;
#endif

    ngx_table_elt_t                  *authorization;

    ngx_table_elt_t                  *keep_alive;

#if (NGX_HTTP_PROXY || NGX_HTTP_REALIP || NGX_HTTP_GEO)
    ngx_table_elt_t                  *x_forwarded_for;
#endif

#if (NGX_HTTP_REALIP)
    ngx_table_elt_t                  *x_real_ip;
#endif

#if (NGX_HTTP_HEADERS)
    ngx_table_elt_t                  *accept;
    ngx_table_elt_t                  *accept_language;
#endif

#if (NGX_HTTP_DAV)
    ngx_table_elt_t                  *depth;
    ngx_table_elt_t                  *destination;
    ngx_table_elt_t                  *overwrite;
    ngx_table_elt_t                  *date;
#endif

    ngx_str_t                         user;
    ngx_str_t                         passwd;
    ngx_array_t                       cookies;

    ngx_str_t                         server;
    off_t                             content_length_n;
    time_t                            keep_alive_n;

    unsigned                          connection_type:2;
    unsigned                          msie:1;
    unsigned                          msie6:1;
    unsigned                          opera:1;
    unsigned                          gecko:1;
    unsigned                          chrome:1;
    unsigned                          safari:1;
    unsigned                          konqueror:1;
} ngx_http_headers_in_t;

接着，该函数会检查进来的请求是否使用的是http0.9，如果是的话则使用从请求行里得到的域名，调用ngx_http_find_virtual_server（）函数来查找用来处理该请求的虚拟服务器配置，之前通过端口和地址找到的默认配置不再使用，找到相应的配置之后，则直接调用ngx_http_process_request（）函数处理该请求，因为http0.9是最原始的http协议，它里面没有定义任何请求头，显然就不需要读取请求头的操作。

if (r->host_start && r->host_end) {
host = r->host_start;
n = ngx_http_validate_host(r, &host,
r->host_end - r->host_start, 0);
if (n == 0) {
ngx_log_error(NGX_LOG_INFO, c->log, 0,
"client sent invalid host in request line");
ngx_http_finalize_request(r, NGX_HTTP_BAD_REQUEST);
return;
}
if (n < 0) {
ngx_http_close_request(r, NGX_HTTP_INTERNAL_SERVER_ERROR);
return;
}
r->headers_in.server.len = n;
r->headers_in.server.data = host;
}
if (r->http_version < NGX_HTTP_VERSION_10) {
if (ngx_http_find_virtual_server(r, r->headers_in.server.data,
r->headers_in.server.len)
== NGX_ERROR)
{
ngx_http_close_request(r, NGX_HTTP_INTERNAL_SERVER_ERROR);
return;
}
ngx_http_process_request(r);
return;
}

            if (r->host_start && r->host_end) {

                host = r->host_start;
                n = ngx_http_validate_host(r, &host,
                                           r->host_end - r->host_start, 0);

                if (n == 0) {
                    ngx_log_error(NGX_LOG_INFO, c->log, 0,
                                  "client sent invalid host in request line");
                    ngx_http_finalize_request(r, NGX_HTTP_BAD_REQUEST);
                    return;
                }

                if (n < 0) {
                    ngx_http_close_request(r, NGX_HTTP_INTERNAL_SERVER_ERROR);
                    return;
                }

                r->headers_in.server.len = n;
                r->headers_in.server.data = host;
            }

            if (r->http_version < NGX_HTTP_VERSION_10) {

                if (ngx_http_find_virtual_server(r, r->headers_in.server.data,
                                                 r->headers_in.server.len)
                    == NGX_ERROR)
                {
                    ngx_http_close_request(r, NGX_HTTP_INTERNAL_SERVER_ERROR);
                    return;
                }

                ngx_http_process_request(r);
                return;
            }

当然，如果是1.0或者更新的http协议，接下来要做的就是读取请求头了，首先nginx会为请求头分配空间，ngx_http_headers_in_t结构的headers字段为一个链表结构，它被用来保存所有请求头，初始为它分配了20个节点，每个节点的类型为ngx_table_elt_t，保存请求头的name/value值对，还可以看到ngx_http_headers_in_t结构有很多类型为ngx_table_elt_t*的指针成员，而且从它们的命名可以看出是一些常见的请求头名字，nginx对这些常用的请求头在ngx_http_headers_in_t结构里面保存了一份引用，后续需要使用的话，可以直接通过这些成员得到，另外也事先为cookie头分配了2个元素的数组空间，做完这些内存准备工作之后，该请求对应的读事件结构的处理函数被设置为ngx_http_process_request_headers，并随后马上调用了该函数。

if (ngx_list_init(&r->headers_in.headers, r->pool, 20,
sizeof(ngx_table_elt_t))
!= NGX_OK)
{
ngx_http_close_request(r, NGX_HTTP_INTERNAL_SERVER_ERROR);
return;
}
if (ngx_array_init(&r->headers_in.cookies, r->pool, 2,
sizeof(ngx_table_elt_t *))
!= NGX_OK)
{
ngx_http_close_request(r, NGX_HTTP_INTERNAL_SERVER_ERROR);
return;
}
c->log->action = "reading client request headers";
rev->handler = ngx_http_process_request_headers;
ngx_http_process_request_headers(rev);

            if (ngx_list_init(&r->headers_in.headers, r->pool, 20,
                              sizeof(ngx_table_elt_t))
                != NGX_OK)
            {
                ngx_http_close_request(r, NGX_HTTP_INTERNAL_SERVER_ERROR);
                return;
            }

            if (ngx_array_init(&r->headers_in.cookies, r->pool, 2,
                               sizeof(ngx_table_elt_t *))
                != NGX_OK)
            {
                ngx_http_close_request(r, NGX_HTTP_INTERNAL_SERVER_ERROR);
                return;
            }

            c->log->action = "reading client request headers";

            rev->handler = ngx_http_process_request_headers;
            ngx_http_process_request_headers(rev);

ngx_http_process_request_headers函数循环的读取所有的请求头，并保存和初始化和请求头相关的结构，下面详细分析一下该函数：
因为nginx对读取请求头有超时限制，ngx_http_process_request_headers函数作为读事件处理函数，一并处理了超时事件，如果读超时了，nginx直接给该请求返回408错误：

[cpp] view plaincopyprint?

if (rev->timedout) {
ngx_log_error(NGX_LOG_INFO, c->log, NGX_ETIMEDOUT, "client timed out");
c->timedout = 1;
ngx_http_close_request(r, NGX_HTTP_REQUEST_TIME_OUT);
return;
}

    if (rev->timedout) {
        ngx_log_error(NGX_LOG_INFO, c->log, NGX_ETIMEDOUT, "client timed out");
        c->timedout = 1;
        ngx_http_close_request(r, NGX_HTTP_REQUEST_TIME_OUT);
        return;
    }

读取和解析请求头的逻辑和处理请求行差不多，总的流程也是循环的调用ngx_http_read_request_header（）函数读取数据，然后再调用一个解析函数来从读取的数据中解析请求头，直到解析完所有请求头，或者发生解析错误为主。当然由于涉及到网络io，这个流程可能发生在多个io事件的上下文中。

接着来细看该函数，先调用了ngx_http_read_request_header（）函数读取数据，如果当前连接并没有数据过来，再直接返回，等待下一次读事件到来，如果读到了一些数据则调用ngx_http_parse_header_line（）函数来解析，同样的该解析函数实现为一个有限状态机，逻辑很简单，只是根据http协议的解析一个请求头的name/vale对，每次调用该函数最多解析出一个请求头，该函数返回4种不同返回值，表示不同解析结果：

1，返回NGX_OK，表示解析出了一行请求头，这时还要判断解析出的请求头名字里面是否有非法字符，名字里面合法的字符包括字母，数字和连字符（-），另外如果设置了underscores_in_headers指令为on，则下划线也是合法字符，但是nginx默认下划线不合法，当请求头里面包含了非法的字符，nginx默认只是忽略这一行请求头；如果一切都正常，nginx会将该请求头及请求头名字的hash值保存在请求结构体的headers_in成员的headers链表,而且对于一些常见的请求头，如Host，Connection，nginx采用了类似于配置指令的方式，事先给这些请求头分配了一个处理函数，当解析出一个请求头时，会检查该请求头是否有设置处理函数，有的话则调用之，nginx所有有处理函数的请求头都记录在ngx_http_headers_in全局数组中：

typedef struct {
ngx_str_t name;
ngx_uint_t offset;
ngx_http_header_handler_pt handler;
} ngx_http_header_t;
ngx_http_header_t ngx_http_headers_in[] = {
{ ngx_string("Host"), offsetof(ngx_http_headers_in_t, host),
ngx_http_process_host },
{ ngx_string("Connection"), offsetof(ngx_http_headers_in_t, connection),
ngx_http_process_connection },
{ ngx_string("If-Modified-Since"),
offsetof(ngx_http_headers_in_t, if_modified_since),
ngx_http_process_unique_header_line },
{ ngx_string("If-Unmodified-Since"),
offsetof(ngx_http_headers_in_t, if_unmodified_since),
ngx_http_process_unique_header_line },
{ ngx_string("User-Agent"), offsetof(ngx_http_headers_in_t, user_agent),
ngx_http_process_user_agent },
{ ngx_string("Referer"), offsetof(ngx_http_headers_in_t, referer),
ngx_http_process_header_line },
{ ngx_string("Content-Length"),
offsetof(ngx_http_headers_in_t, content_length),
ngx_http_process_unique_header_line },
{ ngx_string("Content-Type"),
offsetof(ngx_http_headers_in_t, content_type),
ngx_http_process_header_line },
{ ngx_string("Range"), offsetof(ngx_http_headers_in_t, range),
ngx_http_process_header_line },
{ ngx_string("If-Range"),
offsetof(ngx_http_headers_in_t, if_range),
ngx_http_process_unique_header_line },
{ ngx_string("Transfer-Encoding"),
offsetof(ngx_http_headers_in_t, transfer_encoding),
ngx_http_process_header_line },
{ ngx_string("Expect"),
offsetof(ngx_http_headers_in_t, expect),
ngx_http_process_unique_header_line },
#if (NGX_HTTP_GZIP)
{ ngx_string("Accept-Encoding"),
offsetof(ngx_http_headers_in_t, accept_encoding),
ngx_http_process_header_line },
{ ngx_string("Via"), offsetof(ngx_http_headers_in_t, via),
ngx_http_process_header_line },
#endif
{ ngx_string("Authorization"),
offsetof(ngx_http_headers_in_t, authorization),
ngx_http_process_unique_header_line },
{ ngx_string("Keep-Alive"), offsetof(ngx_http_headers_in_t, keep_alive),
ngx_http_process_header_line },
#if (NGX_HTTP_PROXY || NGX_HTTP_REALIP || NGX_HTTP_GEO)
{ ngx_string("X-Forwarded-For"),
offsetof(ngx_http_headers_in_t, x_forwarded_for),
ngx_http_process_header_line },
#endif
#if (NGX_HTTP_REALIP)
{ ngx_string("X-Real-IP"),
offsetof(ngx_http_headers_in_t, x_real_ip),
ngx_http_process_header_line },
#endif
#if (NGX_HTTP_HEADERS)
{ ngx_string("Accept"), offsetof(ngx_http_headers_in_t, accept),
ngx_http_process_header_line },
{ ngx_string("Accept-Language"),
offsetof(ngx_http_headers_in_t, accept_language),
ngx_http_process_header_line },
#endif
#if (NGX_HTTP_DAV)
{ ngx_string("Depth"), offsetof(ngx_http_headers_in_t, depth),
ngx_http_process_header_line },
{ ngx_string("Destination"), offsetof(ngx_http_headers_in_t, destination),
ngx_http_process_header_line },
{ ngx_string("Overwrite"), offsetof(ngx_http_headers_in_t, overwrite),
ngx_http_process_header_line },
{ ngx_string("Date"), offsetof(ngx_http_headers_in_t, date),
ngx_http_process_header_line },
#endif
{ ngx_string("Cookie"), 0, ngx_http_process_cookie },
{ ngx_null_string, 0, NULL }
};

typedef struct {
    ngx_str_t                         name;
    ngx_uint_t                        offset;
    ngx_http_header_handler_pt        handler;
} ngx_http_header_t;

ngx_http_header_t  ngx_http_headers_in[] = {
    { ngx_string("Host"), offsetof(ngx_http_headers_in_t, host),
                 ngx_http_process_host },

    { ngx_string("Connection"), offsetof(ngx_http_headers_in_t, connection),
                 ngx_http_process_connection },

    { ngx_string("If-Modified-Since"),
                 offsetof(ngx_http_headers_in_t, if_modified_since),
                 ngx_http_process_unique_header_line },

    { ngx_string("If-Unmodified-Since"),
                 offsetof(ngx_http_headers_in_t, if_unmodified_since),
                 ngx_http_process_unique_header_line },

    { ngx_string("User-Agent"), offsetof(ngx_http_headers_in_t, user_agent),
                 ngx_http_process_user_agent },


    { ngx_string("Referer"), offsetof(ngx_http_headers_in_t, referer),
                 ngx_http_process_header_line },

    { ngx_string("Content-Length"),
                 offsetof(ngx_http_headers_in_t, content_length),
                 ngx_http_process_unique_header_line },

    { ngx_string("Content-Type"),
                 offsetof(ngx_http_headers_in_t, content_type),
                 ngx_http_process_header_line },

    { ngx_string("Range"), offsetof(ngx_http_headers_in_t, range),
                 ngx_http_process_header_line },

    { ngx_string("If-Range"),
                 offsetof(ngx_http_headers_in_t, if_range),
                 ngx_http_process_unique_header_line },

    { ngx_string("Transfer-Encoding"),
                 offsetof(ngx_http_headers_in_t, transfer_encoding),
                 ngx_http_process_header_line },

    { ngx_string("Expect"),
                 offsetof(ngx_http_headers_in_t, expect),
                 ngx_http_process_unique_header_line },

#if (NGX_HTTP_GZIP)
    { ngx_string("Accept-Encoding"),
                 offsetof(ngx_http_headers_in_t, accept_encoding),
                 ngx_http_process_header_line },

    { ngx_string("Via"), offsetof(ngx_http_headers_in_t, via),
                 ngx_http_process_header_line },
#endif

    { ngx_string("Authorization"),
                 offsetof(ngx_http_headers_in_t, authorization),
                 ngx_http_process_unique_header_line },

    { ngx_string("Keep-Alive"), offsetof(ngx_http_headers_in_t, keep_alive),
                 ngx_http_process_header_line },


#if (NGX_HTTP_PROXY || NGX_HTTP_REALIP || NGX_HTTP_GEO)
    { ngx_string("X-Forwarded-For"),
                 offsetof(ngx_http_headers_in_t, x_forwarded_for),
                 ngx_http_process_header_line },
#endif

#if (NGX_HTTP_REALIP)
    { ngx_string("X-Real-IP"),
                 offsetof(ngx_http_headers_in_t, x_real_ip),
                 ngx_http_process_header_line },
#endif

#if (NGX_HTTP_HEADERS)
    { ngx_string("Accept"), offsetof(ngx_http_headers_in_t, accept),
                 ngx_http_process_header_line },

    { ngx_string("Accept-Language"),
                 offsetof(ngx_http_headers_in_t, accept_language),
                 ngx_http_process_header_line },
#endif

#if (NGX_HTTP_DAV)
    { ngx_string("Depth"), offsetof(ngx_http_headers_in_t, depth),
                 ngx_http_process_header_line },

    { ngx_string("Destination"), offsetof(ngx_http_headers_in_t, destination),
                 ngx_http_process_header_line },

    { ngx_string("Overwrite"), offsetof(ngx_http_headers_in_t, overwrite),
                 ngx_http_process_header_line },

    { ngx_string("Date"), offsetof(ngx_http_headers_in_t, date),
                 ngx_http_process_header_line },
#endif

    { ngx_string("Cookie"), 0, ngx_http_process_cookie },

    { ngx_null_string, 0, NULL }
};

ngx_http_headers_in数组当前包含了25个常用的请求头，每个请求头都设置了一个处理函数，当前其中一部分请求头设置的是公共的处理函数，这里有2个公共的处理函数，ngx_http_process_header_line和ngx_http_process_unique_header_line。

先来看一下处理函数的函数指针定义：
typedef ngx_int_t (*ngx_http_header_handler_pt)(ngx_http_request_t *r,
ngx_table_elt_t *h, ngx_uint_t offset);
它有3个参数，r为对应的请求结构，h为该请求头在headers_in.headers链表节点的指针，offset为该请求头的引用在ngx_http_headers_in_t结构中的偏移。
再来看ngx_http_process_header_line函数：

[cpp] view plaincopyprint?

static ngx_int_t
ngx_http_process_header_line(ngx_http_request_t *r, ngx_table_elt_t *h,
ngx_uint_t offset)
{
ngx_table_elt_t **ph;
ph = (ngx_table_elt_t **) ((char *) &r->headers_in + offset);
if (*ph == NULL) {
*ph = h;
}
return NGX_OK;
}

static ngx_int_t
ngx_http_process_header_line(ngx_http_request_t *r, ngx_table_elt_t *h,
    ngx_uint_t offset)
{
    ngx_table_elt_t  **ph;

    ph = (ngx_table_elt_t **) ((char *) &r->headers_in + offset);

    if (*ph == NULL) {
        *ph = h;
    }

    return NGX_OK;
}

这个函数只是简单将该请求头在ngx_http_headers_in_t结构中保存一份引用。ngx_http_process_unique_header_line功能类似，不同点在于该函数会检查这个请求头是否是重复的，如果是的话，则给该请求返回400错误。

ngx_http_headers_in数组中剩下的请求头都有自己特殊的处理函数，这些特殊的函数根据对应的请求头有一些特殊的处理，下面我们拿Host头的处理函数ngx_http_process_host做一下介绍：

[cpp] view plaincopyprint?

static ngx_int_t
ngx_http_process_host(ngx_http_request_t *r, ngx_table_elt_t *h,
ngx_uint_t offset)
{
u_char *host;
ssize_t len;
if (r->headers_in.host == NULL) {
r->headers_in.host = h;
}
host = h->value.data;
len = ngx_http_validate_host(r, &host, h->value.len, 0);
if (len == 0) {
ngx_log_error(NGX_LOG_INFO, r->connection->log, 0,
"client sent invalid host header");
ngx_http_finalize_request(r, NGX_HTTP_BAD_REQUEST);
return NGX_ERROR;
}
if (len < 0) {
ngx_http_close_request(r, NGX_HTTP_INTERNAL_SERVER_ERROR);
return NGX_ERROR;
}
if (r->headers_in.server.len) {
return NGX_OK;
}
r->headers_in.server.len = len;
r->headers_in.server.data = host;
return NGX_OK;
}

static ngx_int_t
ngx_http_process_host(ngx_http_request_t *r, ngx_table_elt_t *h,
    ngx_uint_t offset)
{
    u_char   *host;
    ssize_t   len;

    if (r->headers_in.host == NULL) {
        r->headers_in.host = h;
    }

    host = h->value.data;
    len = ngx_http_validate_host(r, &host, h->value.len, 0);

    if (len == 0) {
        ngx_log_error(NGX_LOG_INFO, r->connection->log, 0,
                      "client sent invalid host header");
        ngx_http_finalize_request(r, NGX_HTTP_BAD_REQUEST);
        return NGX_ERROR;
    }

    if (len < 0) {
        ngx_http_close_request(r, NGX_HTTP_INTERNAL_SERVER_ERROR);
        return NGX_ERROR;
    }

    if (r->headers_in.server.len) {
        return NGX_OK;
    }

    r->headers_in.server.len = len;
    r->headers_in.server.data = host;

    return NGX_OK;
}

此函数的目的也是保存Host头的快速引用，它会对Host头的值做一些合法性检查，并从中解析出域名，保存在headers_in.server字段，实际上前面在解析请求行时，headers_in.server可能已经被赋值为从请求行中解析出来的域名，根据http协议的规范，如果请求行中的uri带有域名的话，则域名以它为准，所以这里需检查一下headers_in.server是否为空，如果不为空则不需要再赋值。

其他请求头的特殊处理函数，不再做介绍，大致都是根据该请求头在http协议中规定的意义及其值设置请求的一些属性，必备后续使用。

对一个合法的请求头的处理大致为如上所述；

2，返回NGX_AGAIN，表示当前接收到的数据不够，一行请求头还未结束，需要继续下一轮循环。在下一轮循环中，nginx首先检查请求头缓冲区header_in是否已满，如够满了，则调用ngx_http_alloc_large_header_buffer（）函数分配更多缓冲区，下面分析一下ngx_http_alloc_large_header_buffer函数：

[cpp] view plaincopyprint?

static ngx_int_t
ngx_http_alloc_large_header_buffer(ngx_http_request_t *r,
ngx_uint_t request_line)
{
u_char *old, *new;
ngx_buf_t *b;
ngx_http_connection_t *hc;
ngx_http_core_srv_conf_t *cscf;
ngx_log_debug0(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
"http alloc large header buffer");
/*
* 在解析请求行阶段，如果客户端在发送请求行之前发送了大量回车换行符将
* 缓冲区塞满了，针对这种情况，nginx只是简单的重置缓冲区，丢弃这些垃圾
* 数据，不需要分配更大的内存。
*/
if (request_line && r->state == 0) {
/* the client fills up the buffer with "\r\n" */
r->request_length += r->header_in->end - r->header_in->start;
r->header_in->pos = r->header_in->start;
r->header_in->last = r->header_in->start;
return NGX_OK;
}
/* 保存请求行或者请求头在旧缓冲区中的起始地址 */
old = request_line ? r->request_start : r->header_name_start;
cscf = ngx_http_get_module_srv_conf(r, ngx_http_core_module);
/* 如果一个大缓冲区还装不下请求行或者一个请求头，则返回错误 */
if (r->state != 0
&& (size_t) (r->header_in->pos - old)
>= cscf->large_client_header_buffers.size)
{
return NGX_DECLINED;
}
hc = r->http_connection;
/* 首先在ngx_http_connection_t结构中查找是否有空闲缓冲区，有的话，直接取之 */
if (hc->nfree) {
b = hc->free[--hc->nfree];
ngx_log_debug2(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
"http large header free: %p %uz",
b->pos, b->end - b->last);
/* 检查给该请求分配的请求头缓冲区个数是否已经超过限制，默认最大个数为4个 */
} else if (hc->nbusy < cscf->large_client_header_buffers.num) {
if (hc->busy == NULL) {
hc->busy = ngx_palloc(r->connection->pool,
cscf->large_client_header_buffers.num * sizeof(ngx_buf_t *));
if (hc->busy == NULL) {
return NGX_ERROR;
}
}
/* 如果还没有达到最大分配数量，则分配一个新的大缓冲区 */
b = ngx_create_temp_buf(r->connection->pool,
cscf->large_client_header_buffers.size);
if (b == NULL) {
return NGX_ERROR;
}
ngx_log_debug2(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
"http large header alloc: %p %uz",
b->pos, b->end - b->last);
} else {
/* 如果已经达到最大的分配限制，则返回错误 */
return NGX_DECLINED;
}
/* 将从空闲队列取得的或者新分配的缓冲区加入已使用队列 */
hc->busy[hc->nbusy++] = b;
/*
* 因为nginx中，所有的请求头的保存形式都是指针（起始和结束地址），
* 所以一行完整的请求头必须放在连续的内存块中。如果旧的缓冲区不能
* 再放下整行请求头，则分配新缓冲区，并从旧缓冲区拷贝已经读取的部分请求头，
* 拷贝完之后，需要修改所有相关指针指向到新缓冲区。
* status为0表示解析完一行请求头之后，缓冲区正好被用完，这种情况不需要拷贝
*/
if (r->state == 0) {
/*
* r->state == 0 means that a header line was parsed successfully
* and we do not need to copy incomplete header line and
* to relocate the parser header pointers
*/
r->request_length += r->header_in->end - r->header_in->start;
r->header_in = b;
return NGX_OK;
}
ngx_log_debug1(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
"http large header copy: %d", r->header_in->pos - old);
r->request_length += old - r->header_in->start;
new = b->start;
/* 拷贝旧缓冲区中不完整的请求头 */
ngx_memcpy(new, old, r->header_in->pos - old);
b->pos = new + (r->header_in->pos - old);
b->last = new + (r->header_in->pos - old);
/* 修改相应的指针指向新缓冲区 */
if (request_line) {
r->request_start = new;
if (r->request_end) {
r->request_end = new + (r->request_end - old);
}
r->method_end = new + (r->method_end - old);
r->uri_start = new + (r->uri_start - old);
r->uri_end = new + (r->uri_end - old);
if (r->schema_start) {
r->schema_start = new + (r->schema_start - old);
r->schema_end = new + (r->schema_end - old);
}
if (r->host_start) {
r->host_start = new + (r->host_start - old);
if (r->host_end) {
r->host_end = new + (r->host_end - old);
}
}
if (r->port_start) {
r->port_start = new + (r->port_start - old);
r->port_end = new + (r->port_end - old);
}
if (r->uri_ext) {
r->uri_ext = new + (r->uri_ext - old);
}
if (r->args_start) {
r->args_start = new + (r->args_start - old);
}
if (r->http_protocol.data) {
r->http_protocol.data = new + (r->http_protocol.data - old);
}
} else {
r->header_name_start = new;
r->header_name_end = new + (r->header_name_end - old);
r->header_start = new + (r->header_start - old);
r->header_end = new + (r->header_end - old);
}
r->header_in = b;
return NGX_OK;
}

static ngx_int_t
ngx_http_alloc_large_header_buffer(ngx_http_request_t *r,
    ngx_uint_t request_line)
{
    u_char                    *old, *new;
    ngx_buf_t                 *b;
    ngx_http_connection_t     *hc;
    ngx_http_core_srv_conf_t  *cscf;

    ngx_log_debug0(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
                   "http alloc large header buffer");

    /*
     * 在解析请求行阶段，如果客户端在发送请求行之前发送了大量回车换行符将
     * 缓冲区塞满了，针对这种情况，nginx只是简单的重置缓冲区，丢弃这些垃圾
     * 数据，不需要分配更大的内存。
     */
    if (request_line && r->state == 0) {

        /* the client fills up the buffer with "\r\n" */

        r->request_length += r->header_in->end - r->header_in->start;

        r->header_in->pos = r->header_in->start;
        r->header_in->last = r->header_in->start;

        return NGX_OK;
    }

    /* 保存请求行或者请求头在旧缓冲区中的起始地址 */
    old = request_line ? r->request_start : r->header_name_start;

    cscf = ngx_http_get_module_srv_conf(r, ngx_http_core_module);

    /* 如果一个大缓冲区还装不下请求行或者一个请求头，则返回错误 */
    if (r->state != 0
        && (size_t) (r->header_in->pos - old)
                                     >= cscf->large_client_header_buffers.size)
    {
        return NGX_DECLINED;
    }

    hc = r->http_connection;

    /* 首先在ngx_http_connection_t结构中查找是否有空闲缓冲区，有的话，直接取之 */
    if (hc->nfree) {
        b = hc->free[--hc->nfree];

        ngx_log_debug2(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
                       "http large header free: %p %uz",
                       b->pos, b->end - b->last);

    /* 检查给该请求分配的请求头缓冲区个数是否已经超过限制，默认最大个数为4个 */
    } else if (hc->nbusy < cscf->large_client_header_buffers.num) {

        if (hc->busy == NULL) {
            hc->busy = ngx_palloc(r->connection->pool,
                  cscf->large_client_header_buffers.num * sizeof(ngx_buf_t *));
            if (hc->busy == NULL) {
                return NGX_ERROR;
            }
        }

        /* 如果还没有达到最大分配数量，则分配一个新的大缓冲区 */
        b = ngx_create_temp_buf(r->connection->pool,
                                cscf->large_client_header_buffers.size);
        if (b == NULL) {
            return NGX_ERROR;
        }

        ngx_log_debug2(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
                       "http large header alloc: %p %uz",
                       b->pos, b->end - b->last);

    } else {
        /* 如果已经达到最大的分配限制，则返回错误 */
        return NGX_DECLINED;
    }

    /* 将从空闲队列取得的或者新分配的缓冲区加入已使用队列 */
    hc->busy[hc->nbusy++] = b;

    /*
     * 因为nginx中，所有的请求头的保存形式都是指针（起始和结束地址），
     * 所以一行完整的请求头必须放在连续的内存块中。如果旧的缓冲区不能
     * 再放下整行请求头，则分配新缓冲区，并从旧缓冲区拷贝已经读取的部分请求头，
     * 拷贝完之后，需要修改所有相关指针指向到新缓冲区。
     * status为0表示解析完一行请求头之后，缓冲区正好被用完，这种情况不需要拷贝
     */
    if (r->state == 0) {
        /*
         * r->state == 0 means that a header line was parsed successfully
         * and we do not need to copy incomplete header line and
         * to relocate the parser header pointers
         */

        r->request_length += r->header_in->end - r->header_in->start;

        r->header_in = b;

        return NGX_OK;
    }

    ngx_log_debug1(NGX_LOG_DEBUG_HTTP, r->connection->log, 0,
                   "http large header copy: %d", r->header_in->pos - old);

    r->request_length += old - r->header_in->start;

    new = b->start;

    /* 拷贝旧缓冲区中不完整的请求头 */
    ngx_memcpy(new, old, r->header_in->pos - old);

    b->pos = new + (r->header_in->pos - old);
    b->last = new + (r->header_in->pos - old);

    /* 修改相应的指针指向新缓冲区 */
    if (request_line) {
        r->request_start = new;

        if (r->request_end) {
            r->request_end = new + (r->request_end - old);
        }

        r->method_end = new + (r->method_end - old);

        r->uri_start = new + (r->uri_start - old);
        r->uri_end = new + (r->uri_end - old);

        if (r->schema_start) {
            r->schema_start = new + (r->schema_start - old);
            r->schema_end = new + (r->schema_end - old);
        }

        if (r->host_start) {
            r->host_start = new + (r->host_start - old);
            if (r->host_end) {
                r->host_end = new + (r->host_end - old);
            }
        }

        if (r->port_start) {
            r->port_start = new + (r->port_start - old);
            r->port_end = new + (r->port_end - old);
        }

        if (r->uri_ext) {
            r->uri_ext = new + (r->uri_ext - old);
        }

        if (r->args_start) {
            r->args_start = new + (r->args_start - old);
        }

        if (r->http_protocol.data) {
            r->http_protocol.data = new + (r->http_protocol.data - old);
        }

    } else {
        r->header_name_start = new;
        r->header_name_end = new + (r->header_name_end - old);
        r->header_start = new + (r->header_start - old);
        r->header_end = new + (r->header_end - old);
    }

    r->header_in = b;

    return NGX_OK;
}

当ngx_http_alloc_large_header_buffer函数返回NGX_DECLINED）时，表示客户端发送了过大的一行请求头，或者是整个请求头部超过了限制，nginx会返回494错误，注意到nginx再返回494错误之前将请求的lingering_close标识置为了1，这样做的目的是在返回响应之丢弃掉客户端发过来的其他数据；

3，返回NGX_HTTP_PARSE_INVALID_HEADER，表示请求头解析过程中遇到错误，一般为客户端发送了不符合协议规范的头部，此时nginx返回400错误。

4，返回NGX_HTTP_PARSE_HEADER_DONE，表示所有请求头已经成功的解析，这时请求的状态被设置为NGX_HTTP_PROCESS_REQUEST_STATE，意味着结束了请求读取阶段，正式进入了请求处理阶段，但是实际上请求可能含有请求体，nginx在请求读取阶段并不会去读取请求体，这个工作交给了后续的请求处理阶段的模块，这样做的目的是nginx本身并不知道这些请求体是否有用，如果后续模块并不需要的话，一方面请求体一般较大，如果全部读取进内存，则白白耗费大量的内存空间，另一方面即使nginx将请求体写进磁盘，但是涉及到磁盘io，会耗费比较多时间。所以交由后续模块来决定读取还是丢弃请求体是最明智的办法。

读取完请求头之后，nginx调用了ngx_http_process_request_header（）函数，这个函数主要做了两个方面的事情，一是调用ngx_http_find_virtual_server（）函数查找虚拟服务器配置；二是对一些请求头做一些协议的检查。比如对那些使用http1.1协议但是却没有发送Host头的请求，nginx给这些请求返回400错误。还有nginx现在的版本并不支持chunked格式的输入，如果某些请求申明自己使用了chunked格式的输入（请求带有值为chunked的transfer_encoding头部)，nginx给这些请求返回411错误。等等。
最后调用ngx_http_process_request（）函数处理请求；
至此，nginx接收请求接收流程就介绍完毕。
(责任编辑：IT)

搜索

热门标签:

nginx的请求接收流程（二）