基本流程
1.初始化libuv loop
2.初始化tcp，建立，綁定，監聽
3.設置客戶端連接後的回調函數
4.設置接收到客戶端數據的回調函數
5.進入uv_run(loop, UV_RUN_DEFAULT)事件輪訓
6.在uv__io_poll中通過io複用epoll獲取到發生狀態變化的socket進行處理
文章內容包括:
-
目錄
TCP使用demo
tcp-echo-server.c
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <uv.h>
#define DEFAULT_PORT 7000
#define DEFAULT_BACKLOG 128
uv_loop_t *loop;
struct sockaddr_in addr;
typedef struct {
uv_write_t req;
uv_buf_t buf;
} write_req_t;
void free_write_req(uv_write_t *req) {
write_req_t *wr = (write_req_t*) req;
free(wr->buf.base);
free(wr);
}
void alloc_buffer(uv_handle_t *handle, size_t suggested_size, uv_buf_t *buf) {
buf->base = (char*) malloc(suggested_size);
buf->len = suggested_size;
}
void on_close(uv_handle_t* handle) {
free(handle);
}
void echo_write(uv_write_t *req, int status) {
if (status) {
fprintf(stderr, "Write error %s\n", uv_strerror(status));
}
free_write_req(req);
}
void echo_read(uv_stream_t *client, ssize_t nread, const uv_buf_t *buf) {
if (nread > 0) {
write_req_t *req = (write_req_t*) malloc(sizeof(write_req_t));
req->buf = uv_buf_init(buf->base, nread);
fwrite(buf->base, 30, 1, stdout);
uv_write((uv_write_t*) req, client, &req->buf, 1, echo_write);
return;
}
if (nread < 0) {
if (nread != UV_EOF)
fprintf(stderr, "Read error %s\n", uv_err_name(nread));
uv_close((uv_handle_t*) client, on_close);
}
free(buf->base);
}
void on_new_connection(uv_stream_t *server, int status) {
if (status < 0) {
fprintf(stderr, "New connection error %s\n", uv_strerror(status));
// error!
return;
}
uv_tcp_t *client = (uv_tcp_t*) malloc(sizeof(uv_tcp_t));
uv_tcp_init(loop, client);
if (uv_accept(server, (uv_stream_t*) client) == 0) {
uv_read_start((uv_stream_t*) client, alloc_buffer, echo_read);
}
else {
uv_close((uv_handle_t*) client, on_close);
}
}
int main() {
loop = uv_default_loop();
uv_tcp_t server;
uv_tcp_init(loop, &server);
uv_ip4_addr("0.0.0.0", DEFAULT_PORT, &addr);
uv_tcp_bind(&server, (const struct sockaddr*)&addr, 0);
int r = uv_listen((uv_stream_t*) &server, DEFAULT_BACKLOG, on_new_connection);
if (r) {
fprintf(stderr, "Listen error %s\n", uv_strerror(r));
return 1;
}
return uv_run(loop, UV_RUN_DEFAULT);
}
代碼分析
初始化tcp socket
int uv_tcp_init(uv_loop_t* loop, uv_tcp_t* tcp) {
return uv_tcp_init_ex(loop, tcp, AF_UNSPEC);
}
//初始化，將結構體的一些變量置爲0,NULL之類的
int uv_tcp_init_ex(uv_loop_t* loop, uv_tcp_t* tcp, unsigned int flags) {
int domain;
/* Use the lower 8 bits for the domain */
domain = flags & 0xFF;
if (domain != AF_INET && domain != AF_INET6 && domain != AF_UNSPEC)
return UV_EINVAL;
if (flags & ~0xFF)
return UV_EINVAL;
uv__stream_init(loop, (uv_stream_t*)tcp, UV_TCP);
/* If anything fails beyond this point we need to remove the handle from
* the handle queue, since it was added by uv__handle_init in uv_stream_init.
*/
if (domain != AF_UNSPEC) {
int err = maybe_new_socket(tcp, domain, 0);
if (err) {
QUEUE_REMOVE(&tcp->handle_queue);
return err;
}
}
return 0;
}
創建、綁定、監聽socket
//配置sockaddr參數
int uv_ip4_addr(const char* ip, int port, struct sockaddr_in* addr) {
memset(addr, 0, sizeof(*addr));
addr->sin_family = AF_INET;
addr->sin_port = htons(port);
return uv_inet_pton(AF_INET, ip, &(addr->sin_addr.s_addr));
}
//創建，綁定tcp
int uv__tcp_bind(uv_tcp_t* tcp,
const struct sockaddr* addr,
unsigned int addrlen,
unsigned int flags) {
int err;
int on;
/* Cannot set IPv6-only mode on non-IPv6 socket. */
if ((flags & UV_TCP_IPV6ONLY) && addr->sa_family != AF_INET6)
return UV_EINVAL;
//創建socket
err = maybe_new_socket(tcp, addr->sa_family, 0);
if (err)
return err;
//設置關閉端口後，可以馬上重新使用該端口
on = 1;
if (setsockopt(tcp->io_watcher.fd, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on)))
return UV__ERR(errno);
#ifndef __OpenBSD__
#ifdef IPV6_V6ONLY
if (addr->sa_family == AF_INET6) {
on = (flags & UV_TCP_IPV6ONLY) != 0;
if (setsockopt(tcp->io_watcher.fd,
IPPROTO_IPV6,
IPV6_V6ONLY,
&on,
sizeof on) == -1) {
#if defined(__MVS__)
if (errno == EOPNOTSUPP)
return UV_EINVAL;
#endif
return UV__ERR(errno);
}
}
#endif
#endif
errno = 0;
//綁定
if (bind(tcp->io_watcher.fd, addr, addrlen) && errno != EADDRINUSE) {
if (errno == EAFNOSUPPORT)
/* OSX, other BSDs and SunoS fail with EAFNOSUPPORT when binding a
* socket created with AF_INET to an AF_INET6 address or vice versa. */
return UV_EINVAL;
return UV__ERR(errno);
}
tcp->delayed_error = UV__ERR(errno);
tcp->flags |= UV_HANDLE_BOUND;
if (addr->sa_family == AF_INET6)
tcp->flags |= UV_HANDLE_IPV6;
return 0;
}
//uv_connection_cb cb 爲客戶端連接後的回調函數,backlog爲連接端口號
int uv_listen(uv_stream_t* stream, int backlog, uv_connection_cb cb) {
int err;
switch (stream->type) {
case UV_TCP:
//設置監聽
err = uv_tcp_listen((uv_tcp_t*)stream, backlog, cb);
break;
case UV_NAMED_PIPE:
err = uv_pipe_listen((uv_pipe_t*)stream, backlog, cb);
break;
default:
err = UV_EINVAL;
}
if (err == 0)
uv__handle_start(stream);
return err;
}
int uv_tcp_listen(uv_tcp_t* tcp, int backlog, uv_connection_cb cb) {
static int single_accept = -1;
unsigned long flags;
int err;
if (tcp->delayed_error)
return tcp->delayed_error;
if (single_accept == -1) {
const char* val = getenv("UV_TCP_SINGLE_ACCEPT");
single_accept = (val != NULL && atoi(val) != 0); /* Off by default. */
}
if (single_accept)
tcp->flags |= UV_HANDLE_TCP_SINGLE_ACCEPT;
flags = 0;
#if defined(__MVS__)
/* on zOS the listen call does not bind automatically
if the socket is unbound. Hence the manual binding to
an arbitrary port is required to be done manually
*/
flags |= UV_HANDLE_BOUND;
#endif
err = maybe_new_socket(tcp, AF_INET, flags);
if (err)
return err;
if (listen(tcp->io_watcher.fd, backlog))
return UV__ERR(errno);
tcp->connection_cb = cb;
tcp->flags |= UV_HANDLE_BOUND;
/* Start listening for connections. */
tcp->io_watcher.cb = uv__server_io;
//socket開始工作
//POLLIN 表示tcp socket io接收的事件爲可讀事件，POLLIN保存在pevents中
uv__io_start(tcp->loop, &tcp->io_watcher, POLLIN);
return 0;
}
相關數據保存在io_watcher中
uv__io_start
pevents:行將發生的事件
events:當前發生的事件
詳細可見 https://blog.csdn.net/zouwm12/article/details/101386446
typedef struct uv__io_s uv__io_t;
struct uv__io_s {
uv__io_cb cb;
void* pending_queue[2];
void* watcher_queue[2];
unsigned int pevents; /* Pending event mask i.e. mask at next tick. */
unsigned int events; /* Current event mask. */
int fd;
UV_IO_PRIVATE_PLATFORM_FIELDS
};
void uv__io_start(uv_loop_t* loop, uv__io_t* w, unsigned int events) {
assert(0 == (events & ~(POLLIN | POLLOUT | UV__POLLRDHUP | UV__POLLPRI)));
assert(0 != events);
assert(w->fd >= 0);
assert(w->fd < INT_MAX);
w->pevents |= events;
//如果原來的loop->watchers空間不足，則重新申請空間
maybe_resize(loop, w->fd + 1);
#if !defined(__sun)
/* The event ports backend needs to rearm all file descriptors on each and
* every tick of the event loop but the other backends allow us to
* short-circuit here if the event mask is unchanged.
*/
//如果events和pevents相同，則不再處理
if (w->events == w->pevents)
return;
#endif
if (QUEUE_EMPTY(&w->watcher_queue))
QUEUE_INSERT_TAIL(&loop->watcher_queue, &w->watcher_queue);
//將當前io事件加入loop的watchers
if (loop->watchers[w->fd] == NULL) {
loop->watchers[w->fd] = w;
loop->nfds++;
}
}
socket數據連接
//處理libuv的事件
int uv_run(uv_loop_t* loop, uv_run_mode mode)；
//處理socket事件
void uv__io_poll(uv_loop_t* loop, int timeout)；
void uv__io_poll(uv_loop_t* loop, int timeout) {
/* A bug in kernels < 2.6.37 makes timeouts larger than ~30 minutes
* effectively infinite on 32 bits architectures. To avoid blocking
* indefinitely, we cap the timeout and poll again if necessary.
*
* Note that "30 minutes" is a simplification because it depends on
* the value of CONFIG_HZ. The magic constant assumes CONFIG_HZ=1200,
* that being the largest value I have seen in the wild (and only once.)
*/
static const int max_safe_timeout = 1789569;
struct epoll_event events[1024];
struct epoll_event* pe;
struct epoll_event e;
int real_timeout;
QUEUE* q;
uv__io_t* w;
sigset_t sigset;
sigset_t* psigset;
uint64_t base;
int have_signals;
int nevents;
int count;
int nfds;
int fd;
int op;
int i;
if (loop->nfds == 0) {
assert(QUEUE_EMPTY(&loop->watcher_queue));
return;
}
memset(&e, 0, sizeof(e));
//從隊列watcher_queue中取出fd，加入epoll
while (!QUEUE_EMPTY(&loop->watcher_queue)) {
q = QUEUE_HEAD(&loop->watcher_queue);
QUEUE_REMOVE(q);
QUEUE_INIT(q);
w = QUEUE_DATA(q, uv__io_t, watcher_queue);
assert(w->pevents != 0);
assert(w->fd >= 0);
assert(w->fd < (int) loop->nwatchers);
e.events = w->pevents;
e.data.fd = w->fd;
if (w->events == 0)
op = EPOLL_CTL_ADD;
else
op = EPOLL_CTL_MOD;
/* XXX Future optimization: do EPOLL_CTL_MOD lazily if we stop watching
* events, skip the syscall and squelch the events after epoll_wait().
*/
if (epoll_ctl(loop->backend_fd, op, w->fd, &e)) {
if (errno != EEXIST)
abort();
assert(op == EPOLL_CTL_ADD);
/* We've reactivated a file descriptor that's been watched before. */
if (epoll_ctl(loop->backend_fd, EPOLL_CTL_MOD, w->fd, &e))
abort();
}
//將events賦值爲pevents。由上文可知，此時tcp socket的pevents爲POLLIN
w->events = w->pevents;
}
psigset = NULL;
if (loop->flags & UV_LOOP_BLOCK_SIGPROF) {
sigemptyset(&sigset);
sigaddset(&sigset, SIGPROF);
psigset = &sigset;
}
assert(timeout >= -1);
base = loop->time;
count = 48; /* Benchmarks suggest this gives the best throughput. */
real_timeout = timeout;
for (;;) {
/* See the comment for max_safe_timeout for an explanation of why
* this is necessary. Executive summary: kernel bug workaround.
*/
if (sizeof(int32_t) == sizeof(long) && timeout >= max_safe_timeout)
timeout = max_safe_timeout;
nfds = epoll_pwait(loop->backend_fd,
events,
ARRAY_SIZE(events),
timeout,
psigset);
/* Update loop->time unconditionally. It's tempting to skip the update when
* timeout == 0 (i.e. non-blocking poll) but there is no guarantee that the
* operating system didn't reschedule our process while in the syscall.
*/
SAVE_ERRNO(uv__update_time(loop));
if (nfds == 0) {
assert(timeout != -1);
if (timeout == 0)
return;
/* We may have been inside the system call for longer than |timeout|
* milliseconds so we need to update the timestamp to avoid drift.
*/
goto update_timeout;
}
if (nfds == -1) {
if (errno != EINTR)
abort();
if (timeout == -1)
continue;
if (timeout == 0)
return;
/* Interrupted by a signal. Update timeout and poll again. */
goto update_timeout;
}
//執行到這裏，說明有客戶端連上來了
have_signals = 0;
nevents = 0;
assert(loop->watchers != NULL);
loop->watchers[loop->nwatchers] = (void*) events;
loop->watchers[loop->nwatchers + 1] = (void*) (uintptr_t) nfds;
for (i = 0; i < nfds; i++) {
pe = events + i;
fd = pe->data.fd;
/* Skip invalidated events, see uv__platform_invalidate_fd */
if (fd == -1)
continue;
assert(fd >= 0);
assert((unsigned) fd < loop->nwatchers);
//fd爲tcp socket()創建的fd,根據fd，取出之前保存在watchers的uv__io_t
w = loop->watchers[fd];
if (w == NULL) {
/* File descriptor that we've stopped watching, disarm it.
*
* Ignore all errors because we may be racing with another thread
* when the file descriptor is closed.
*/
epoll_ctl(loop->backend_fd, EPOLL_CTL_DEL, fd, pe);
continue;
}
/* Give users only events they're interested in. Prevents spurious
* callbacks when previous callback invocation in this loop has stopped
* the current watcher. Also, filters out events that users has not
* requested us to watch.
*/
pe->events &= w->pevents | POLLERR | POLLHUP;
/* Work around an epoll quirk where it sometimes reports just the
* EPOLLERR or EPOLLHUP event. In order to force the event loop to
* move forward, we merge in the read/write events that the watcher
* is interested in; uv__read() and uv__write() will then deal with
* the error or hangup in the usual fashion.
*
* Note to self: happens when epoll reports EPOLLIN|EPOLLHUP, the user
* reads the available data, calls uv_read_stop(), then sometime later
* calls uv_read_start() again. By then, libuv has forgotten about the
* hangup and the kernel won't report EPOLLIN again because there's
* nothing left to read. If anything, libuv is to blame here. The
* current hack is just a quick bandaid; to properly fix it, libuv
* needs to remember the error/hangup event. We should get that for
* free when we switch over to edge-triggered I/O.
*/
if (pe->events == POLLERR || pe->events == POLLHUP)
pe->events |=
w->pevents & (POLLIN | POLLOUT | UV__POLLRDHUP | UV__POLLPRI);
if (pe->events != 0) {
/* Run signal watchers last. This also affects child process watchers
* because those are implemented in terms of signal watchers.
*/
if (w == &loop->signal_io_watcher)
have_signals = 1;
else
//調用server socket的回調函數，該回調函數在uv_tcp_listen中註冊，函數名
//爲uv__server_io
w->cb(loop, w, pe->events);
nevents++;
}
}
if (have_signals != 0)
loop->signal_io_watcher.cb(loop, &loop->signal_io_watcher, POLLIN);
loop->watchers[loop->nwatchers] = NULL;
loop->watchers[loop->nwatchers + 1] = NULL;
if (have_signals != 0)
return; /* Event loop should cycle now so don't poll again. */
if (nevents != 0) {
if (nfds == ARRAY_SIZE(events) && --count != 0) {
/* Poll for more events but don't block this time. */
timeout = 0;
continue;
}
return;
}
if (timeout == 0)
return;
if (timeout == -1)
continue;
update_timeout:
assert(timeout > 0);
real_timeout -= (loop->time - base);
if (real_timeout <= 0)
return;
timeout = real_timeout;
}
}
執行uv__server_io
void uv__server_io(uv_loop_t* loop, uv__io_t* w, unsigned int events) {
uv_stream_t* stream;
int err;
stream = container_of(w, uv_stream_t, io_watcher);
assert(events & POLLIN);
assert(stream->accepted_fd == -1);
assert(!(stream->flags & UV_HANDLE_CLOSING));
//由上文可知，stream的events==pevents，uv__io_start沒做什麼就直接返回了
uv__io_start(stream->loop, &stream->io_watcher, POLLIN);
/* connection_cb can close the server socket while we're
* in the loop so check it on each iteration.
*/
while (uv__stream_fd(stream) != -1) {
assert(stream->accepted_fd == -1);
#if defined(UV_HAVE_KQUEUE)
if (w->rcount <= 0)
return;
#endif /* defined(UV_HAVE_KQUEUE) */
//獲取客戶端連接上來的fd,進入uv__accept發現linux上不是使用accept函數
//而是調用syscall來執行系統調用，直接讓內核來處理，顯得更加高效
err = uv__accept(uv__stream_fd(stream));
if (err < 0) {
if (err == UV_EAGAIN || err == UV__ERR(EWOULDBLOCK))
return; /* Not an error. */
if (err == UV_ECONNABORTED)
continue; /* Ignore. Nothing we can do about that. */
if (err == UV_EMFILE || err == UV_ENFILE) {
err = uv__emfile_trick(loop, uv__stream_fd(stream));
if (err == UV_EAGAIN || err == UV__ERR(EWOULDBLOCK))
break;
}
stream->connection_cb(stream, err);
continue;
}
UV_DEC_BACKLOG(w)
stream->accepted_fd = err;
//執行連接的回調函數，函數在demo中註冊
stream->connection_cb(stream, 0);
if (stream->accepted_fd != -1) {
/* The user hasn't yet accepted called uv_accept() */
uv__io_stop(loop, &stream->io_watcher, POLLIN);
return;
}
if (stream->type == UV_TCP &&
(stream->flags & UV_HANDLE_TCP_SINGLE_ACCEPT)) {
/* Give other processes a chance to accept connections. */
struct timespec timeout = { 0, 1 };
nanosleep(&timeout, NULL);
}
}
}
connect回調函數
uv_listen((uv_stream_t*) &server, DEFAULT_BACKLOG, on_new_connection)
在main中完成註冊，connection_cb即爲on_new_connection
void on_new_connection(uv_stream_t *server, int status) {
if (status < 0) {
fprintf(stderr, "New connection error %s\n", uv_strerror(status));
// error!
return;
}
//新建一個客戶端的uv_tcp_t
uv_tcp_t *client = (uv_tcp_t*) malloc(sizeof(uv_tcp_t));
uv_tcp_init(loop, client);
if (uv_accept(server, (uv_stream_t*) client) == 0) {
uv_read_start((uv_stream_t*) client, alloc_buffer, echo_read);
}
else {
uv_close((uv_handle_t*) client, on_close);
}
}
建立一個客戶端的uv_tcp_t，flag設置爲UV_HANDLE_READABLE | UV_HANDLE_WRITABLE，將套接字加入到watchers進行監聽，在下一次事件輪訓中，將客戶端加入到epoll中