| 重要过程 | 源码 |
|---|---|
| 1. 初始化客户端链表 | server.clients = listCreate(); |
| 创建数据库字典 |  |
| 创建事件循环 | server.el = aeCreateEventLoop(server.maxclients+CONFIG_FDSET_INCR); |
| 创建socket启动监听 | 创建文件事件 aeCreateFileEvent(server.el, server.ipfd[j], AE_READABLE,acceptTcpHandler,NULL) |
| 监听端口 | if (server.port != 0 && listenToPort(server.port,server.ipfd,&server.ipfd_count) == C_ERR) |
| 创建serverCron时间事件 | if (aeCreateTimeEvent(server.el, 1, serverCron, NULL, NULL) == AE_ERR) |
| 创建事件文件 | if (aeCreateFileEvent(server.el, server.ipfd[j], AE_READABLE,acceptTcpHandler,NULL) == AE_ERR) |
| 集群初始化 |  |
server.c
void initServer(void) {
int j;
signal(SIGHUP, SIG_IGN);
signal(SIGPIPE, SIG_IGN);
setupSignalHandlers();
if (server.syslog_enabled) {
openlog(server.syslog_ident, LOG_PID | LOG_NDELAY | LOG_NOWAIT,
server.syslog_facility);
}
server.hz = server.config_hz;
server.pid = getpid();
server.current_client = NULL;
server.clients = listCreate();
server.clients_index = raxNew();
server.clients_to_close = listCreate();//1初始化客户端链表
server.slaves = listCreate();
server.monitors = listCreate();
server.clients_pending_write = listCreate();
server.slaveseldb = -1; /* Force to emit the first SELECT command. */
server.unblocked_clients = listCreate();
server.ready_keys = listCreate();
server.clients_waiting_acks = listCreate();
server.get_ack_from_slaves = 0;
server.clients_paused = 0;
server.system_memory_size = zmalloc_get_memory_size();
createSharedObjects();
adjustOpenFilesLimit();
server.el = aeCreateEventLoop(server.maxclients+CONFIG_FDSET_INCR);//3. 创建事件循环
if (server.el == NULL) {
serverLog(LL_WARNING,
"Failed creating the event loop. Error message: '%s'",
strerror(errno));
exit(1);
}
//2.
server.db = zmalloc(sizeof(redisDb)*server.dbnum);
/* Open the TCP listening socket for the user commands. */
//4. 监听端口
if (server.port != 0 &&
listenToPort(server.port,server.ipfd,&server.ipfd_count) == C_ERR)
exit(1);
/* Open the listening Unix domain socket. */
if (server.unixsocket != NULL) {
unlink(server.unixsocket); /* don't care if this fails */
server.sofd = anetUnixServer(server.neterr,server.unixsocket,
server.unixsocketperm, server.tcp_backlog);
if (server.sofd == ANET_ERR) {
serverLog(LL_WARNING, "Opening Unix socket: %s", server.neterr);
exit(1);
}
anetNonBlock(NULL,server.sofd);
}
/* Abort if there are no listening sockets at all. */
if (server.ipfd_count == 0 && server.sofd < 0) {
serverLog(LL_WARNING, "Configured to not listen anywhere, exiting.");
exit(1);
}
/* Create the Redis databases, and initialize other internal state. */
for (j = 0; j < server.dbnum; j++) {
server.db[j].dict = dictCreate(&dbDictType,NULL);
server.db[j].expires = dictCreate(&keyptrDictType,NULL);
server.db[j].blocking_keys = dictCreate(&keylistDictType,NULL);
server.db[j].ready_keys = dictCreate(&objectKeyPointerValueDictType,NULL);
server.db[j].watched_keys = dictCreate(&keylistDictType,NULL);
server.db[j].id = j;
server.db[j].avg_ttl = 0;
server.db[j].defrag_later = listCreate();
}
evictionPoolAlloc(); /* Initialize the LRU keys pool. */
server.pubsub_channels = dictCreate(&keylistDictType,NULL);
server.pubsub_patterns = listCreate();
listSetFreeMethod(server.pubsub_patterns,freePubsubPattern);
listSetMatchMethod(server.pubsub_patterns,listMatchPubsubPattern);
server.cronloops = 0;
server.rdb_child_pid = -1;
server.aof_child_pid = -1;
server.rdb_child_type = RDB_CHILD_TYPE_NONE;
server.rdb_bgsave_scheduled = 0;
server.child_info_pipe[0] = -1;
server.child_info_pipe[1] = -1;
server.child_info_data.magic = 0;
aofRewriteBufferReset();
server.aof_buf = sdsempty();
server.lastsave = time(NULL); /* At startup we consider the DB saved. */
server.lastbgsave_try = 0; /* At startup we never tried to BGSAVE. */
server.rdb_save_time_last = -1;
server.rdb_save_time_start = -1;
server.dirty = 0;
resetServerStats();
/* A few stats we don't want to reset: server startup time, and peak mem. */
server.stat_starttime = time(NULL);
server.stat_peak_memory = 0;
server.stat_rdb_cow_bytes = 0;
server.stat_aof_cow_bytes = 0;
server.cron_malloc_stats.zmalloc_used = 0;
server.cron_malloc_stats.process_rss = 0;
server.cron_malloc_stats.allocator_allocated = 0;
server.cron_malloc_stats.allocator_active = 0;
server.cron_malloc_stats.allocator_resident = 0;
server.lastbgsave_status = C_OK;
server.aof_last_write_status = C_OK;
server.aof_last_write_errno = 0;
server.repl_good_slaves_count = 0;
/* Create the timer callback, this is our way to process many background
* operations incrementally, like clients timeout, eviction of unaccessed
* expired keys and so forth. */
if (aeCreateTimeEvent(server.el, 1, serverCron, NULL, NULL) == AE_ERR) {
serverPanic("Can't create event loop timers.");
exit(1);
}
/* Create an event handler for accepting new connections in TCP and Unix
* domain sockets. */
* 5. 创建事件文件
for (j = 0; j < server.ipfd_count; j++) {
if (aeCreateFileEvent(server.el, server.ipfd[j], AE_READABLE,
acceptTcpHandler,NULL) == AE_ERR)
{
serverPanic(
"Unrecoverable error creating server.ipfd file event.");
}
}
if (server.sofd > 0 && aeCreateFileEvent(server.el,server.sofd,AE_READABLE,
acceptUnixHandler,NULL) == AE_ERR) serverPanic("Unrecoverable error creating server.sofd file event.");
/* Register a readable event for the pipe used to awake the event loop
* when a blocked client in a module needs attention. */
if (aeCreateFileEvent(server.el, server.module_blocked_pipe[0], AE_READABLE,
moduleBlockedClientPipeReadable,NULL) == AE_ERR) {
serverPanic(
"Error registering the readable event for the module "
"blocked clients subsystem.");
}
/* Open the AOF file if needed. */
if (server.aof_state == AOF_ON) {
server.aof_fd = open(server.aof_filename,
O_WRONLY|O_APPEND|O_CREAT,0644);
if (server.aof_fd == -1) {
serverLog(LL_WARNING, "Can't open the append-only file: %s",
strerror(errno));
exit(1);
}
}
/* 32 bit instances are limited to 4GB of address space, so if there is
* no explicit limit in the user provided configuration we set a limit
* at 3 GB using maxmemory with 'noeviction' policy'. This avoids
* useless crashes of the Redis instance for out of memory. */
if (server.arch_bits == 32 && server.maxmemory == 0) {
serverLog(LL_WARNING,"Warning: 32 bit instance detected but no memory limit set. Setting 3 GB maxmemory limit with 'noeviction' policy now.");
server.maxmemory = 3072LL*(1024*1024); /* 3 GB */
server.maxmemory_policy = MAXMEMORY_NO_EVICTION;
}
if (server.cluster_enabled) clusterInit();
replicationScriptCacheInit();
scriptingInit(1);
slowlogInit();
latencyMonitorInit();
bioInit();
server.initial_memory_usage = zmalloc_used_memory();
}
aeCreateEventLoop
server.el = aeCreateEventLoop(server.maxclients+CONFIG_FDSET_INCR);
/**
输入参数setsize理论上等于用户配置的最大客户端数目即可，但是为了确保安全，这里设置setsize等于最大客户端数目加128。函数aeApiCreate内部调用epoll_create创建epoll，并初始化结构体eventLoop的字段apidata。
*/
ae.c
aeEventLoop *aeCreateEventLoop(int setsize) {
aeEventLoop *eventLoop;
int i;
if ((eventLoop = zmalloc(sizeof(*eventLoop))) == NULL) goto err;
eventLoop->events = zmalloc(sizeof(aeFileEvent)*setsize);
eventLoop->fired = zmalloc(sizeof(aeFiredEvent)*setsize);
if (eventLoop->events == NULL || eventLoop->fired == NULL) goto err;
eventLoop->setsize = setsize;
eventLoop->lastTime = time(NULL);
eventLoop->timeEventHead = NULL;
eventLoop->timeEventNextId = 0;
eventLoop->stop = 0;
eventLoop->maxfd = -1;
eventLoop->beforesleep = NULL;
eventLoop->aftersleep = NULL;
if (aeApiCreate(eventLoop) == -1) goto err; //4.1
/* Events with mask == AE_NONE are not set. So let's initialize the
* vector with it. */
for (i = 0; i < setsize; i++)
eventLoop->events[i].mask = AE_NONE;
return eventLoop;
err:
if (eventLoop) {
zfree(eventLoop->events);
zfree(eventLoop->fired);
zfree(eventLoop);
}
return NULL;
}
aeApiCreate
aeApiCreate(eventLoop)
typedef struct aeApiState {
//其中epfd函数epoll_create返回的epoll文件描述符，events存储epoll_wait函数返回时已触发的事件数组。
int epfd;
struct epoll_event *events;
} aeApiState;
static int aeApiCreate(aeEventLoop *eventLoop) {
aeApiState *state = zmalloc(sizeof(aeApiState));
if (!state) return -1;
/* 初始化epoll就绪事件表 */
state->events = zmalloc(sizeof(struct epoll_event)*eventLoop->setsize);
if (!state->events) {
zfree(state);
return -1;
}
/* 创建 epoll 实例 */
state->epfd = epoll_create(1024); /* 1024 is just a hint for the kernel */
if (state->epfd == -1) {
zfree(state->events);
zfree(state);
return -1;
}
/* 事件管理器与epoll关联 */
eventLoop->apidata = state;
return 0;
}
listenToPort
输入参数port表示用户配置的端口号，server结构体的bindaddr_count字段存储用户配置的IP地址数目，bindaddr字段存储用户配置的所有IP地址。函数anetTcpServer实现了socket的创建、绑定，以及监听流程，这里不过多详述。参数fds与count可用作输出参数，fds数组存储创建的所有socket文件描述符，count存储socket数目。
注意：所有创建的socket都会设置为非阻塞模式，原因在于Redis使用了IO多路复用模式，其要求socket读写必须是非阻塞的，函数anetNonBlock通过系统调用fcntl设置socket非阻塞模式。
/* Initialize a set of file descriptors to listen to the specified 'port'
* binding the addresses specified in the Redis server configuration.
*
* The listening file descriptors are stored in the integer array 'fds'
* and their number is set in '*count'.
*
* The addresses to bind are specified in the global server.bindaddr array
* and their number is server.bindaddr_count. If the server configuration
* contains no specific addresses to bind, this function will try to
* bind * (all addresses) for both the IPv4 and IPv6 protocols.
*
* On success the function returns C_OK.
*
* On error the function returns C_ERR. For the function to be on
* error, at least one of the server.bindaddr addresses was
* impossible to bind, or no bind addresses were specified in the server
* configuration but the function is not able to bind * for at least
* one of the IPv4 or IPv6 protocols. */
int listenToPort(int port, int *fds, int *count) {
int j;
/* Force binding of 0.0.0.0 if no bind address is specified, always
* entering the loop if j == 0. */
if (server.bindaddr_count == 0) server.bindaddr[0] = NULL;
for (j = 0; j < server.bindaddr_count || j == 0; j++) {
if (server.bindaddr[j] == NULL) {
int unsupported = 0;
/* Bind * for both IPv6 and IPv4, we enter here only if
* server.bindaddr_count == 0. */
fds[*count] = anetTcp6Server(server.neterr,port,NULL,
server.tcp_backlog);
//创建socket并启动监听
if (fds[*count] != ANET_ERR) {
//设置socket非阻塞
anetNonBlock(NULL,fds[*count]);
(*count)++;
} else if (errno == EAFNOSUPPORT) {
unsupported++;
serverLog(LL_WARNING,"Not listening to IPv6: unsupproted");
}
if (*count == 1 || unsupported) {
/* Bind the IPv4 address as well. */
fds[*count] = anetTcpServer(server.neterr,port,NULL,
server.tcp_backlog);
if (fds[*count] != ANET_ERR) {
anetNonBlock(NULL,fds[*count]);
(*count)++;
} else if (errno == EAFNOSUPPORT) {
unsupported++;
serverLog(LL_WARNING,"Not listening to IPv4: unsupproted");
}
}
/* Exit the loop if we were able to bind * on IPv4 and IPv6,
* otherwise fds[*count] will be ANET_ERR and we'll print an
* error and return to the caller with an error. */
if (*count + unsupported == 2) break;
} else if (strchr(server.bindaddr[j],':')) {
/* Bind IPv6 address. */
fds[*count] = anetTcp6Server(server.neterr,port,server.bindaddr[j],
server.tcp_backlog);
} else {
/* Bind IPv4 address. */
fds[*count] = anetTcpServer(server.neterr,port,server.bindaddr[j],
server.tcp_backlog);
}
if (fds[*count] == ANET_ERR) {
serverLog(LL_WARNING,
"Creating Server TCP listening socket %s:%d: %s",
server.bindaddr[j] ? server.bindaddr[j] : "*",
port, server.neterr);
return C_ERR;
}
anetNonBlock(NULL,fds[*count]);
(*count)++;
}
return C_OK;
}
创建文件读写事件
socket的读写事件被抽象为文件事件，因为对于监听的socket还需要创建对应的文件事件。
/* State of an event based program */
typedef struct aeEventLoop {
int maxfd; /* highest file descriptor currently registered */
int setsize; /* max number of file descriptors tracked */
long long timeEventNextId;
time_t lastTime; /* Used to detect system clock skew */
aeFileEvent *events; /* Registered events */
aeFiredEvent *fired; /* Fired events */
aeTimeEvent *timeEventHead;
int stop;
void *apidata; /* This is used for polling API specific data */
aeBeforeSleepProc *beforesleep;
aeBeforeSleepProc *aftersleep;
} aeEventLoop;
结构体aeEventLoop有一个关键字段events，类型为aeFileEvent数组，存储所有需要监控的文件事件。文件事件结构体定义如下：
/* File event structure */
typedef struct aeFileEvent {
存储监控的文件事件类型，如AE_READABLE可读事件和AE_WRITABLE可写事件；
int mask; /* one of AE_(READABLE|WRITABLE|BARRIER) */
为函数指针，指向读事件处理函数
aeFileProc *rfileProc;
同样为函数指针，指向写事件处理函数；
aeFileProc *wfileProc;
指向对应的客户端对象
void *clientData;
} aeFileEvent;
aeCreateFileEvent(server.el, server.ipfd[j], AE_READABLE,
acceptTcpHandler,NULL)
int aeCreateFileEvent(aeEventLoop *eventLoop, int fd, int mask,
aeFileProc *proc, void *clientData)
{
if (fd >= eventLoop->setsize) {
errno = ERANGE;
return AE_ERR;
}
aeFileEvent *fe = &eventLoop->events[fd];
if (aeApiAddEvent(eventLoop, fd, mask) == -1)
return AE_ERR;
fe->mask |= mask;
if (mask & AE_READABLE) fe->rfileProc = proc;
if (mask & AE_WRITABLE) fe->wfileProc = proc;
fe->clientData = clientData;
if (fd > eventLoop->maxfd)
eventLoop->maxfd = fd;
return AE_OK;
}
Redis服务器启动时需要创建socket并监听，等待客户端连接；客户端与服务器建立socket连接之后，服务器会等待客户端的命令请求；服务器处理完客户端的命令请求之后，命令回复会暂时缓存在client结构体的buf缓冲区，待客户端文件描述符的可写事件发生时，才会真正往客户端发送命令回复。这些都需要创建对应的文件事件：
集群初始化
if (server.cluster_enabled) clusterInit();
集群模式 处理
扫一扫
753
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
