本文深入解析Redis的启动流程、IO模型及客户端请求处理过程，并详细介绍其数据结构dict的实现。
第一节.参考
https://www.cnblogs.com/davidwang456/articles/9294912.html
https://blog.youkuaiyun.com/BigRat_WH/article/details/88640793
https://www.cnblogs.com/gjc592/p/11098047.html
https://www.cnblogs.com/cnxkey/articles/7963660.html
编译时，如果报""system_error": 不是 "std" 的成员",加入#include <system_error>.
运行时，如果报"division by zero"异常，修改编译环境为32位.
第二节.架构
一.Reactor模式
结构如下图:
事前驱动的回调模式.
二.持久化
1.rdb
redis database.在指定的时间间隔内，执行指定次数的写操作，则会将内存中的数据写入到磁盘中。即在指定目
录下生成一个dump.rdb文件。Redis重启会通过加载dump.rdb文件恢复数据。比如save 900 1,900秒内有一个更改.备份时会独立创建一个子进程，将数据写入到一个临时文件（此时内存中的数据是原来的两倍），最后再将临时文件替换之前的备份文件。
2.aof
APPEND ONLY MODE.采用日志的形式来记录每个写操作，并追加到文件中。Redis重启时会根据日志文件的内容将写指令从前到后执行一次以完成数据的恢复工作。重写的原理：Redis会fork出一条新进程，读取内存中的数据，并重新写到一个临时文件中。并没有读取旧文件（j旧文件太大）。最后替换旧的aof文件.当AOF文件大小是上次rewrite后大小的一倍且文件大于64M时触发.
三.集群模式
(一).主从模式
(二).哨兵模式
(三).集群模式
Twemproxy,Codis,Redis Cluster不同的槽位处理方式.
四.事务
五.发布订阅
六.使用场景
1.红锁
2.zset
3.luo脚本
第三节.源码细节
一.redis启动
int main(int argc, char **argv) {
struct timeval tv;
int j;
//去掉测试代码
...
//设置进程名
/* We need to initialize our libraries, and the server configuration. */
#ifdef INIT_SETPROCTITLE_REPLACEMENT
spt_init(argc, argv);
#endif
//设置本地化
setlocale(LC_COLLATE,"");
tzset(); /* Populates 'timezone' global. */
//内存溢出是调用redisOutOfMemoryHandler方法打印日志
zmalloc_set_oom_handler(redisOutOfMemoryHandler);
//以进程pid和时间初始化随机数发生器
srand(time(NULL)^getpid());
//获取当前时间
gettimeofday(&tv,NULL);
char hashseed[16];
getRandomHexChars(hashseed,sizeof(hashseed));
dictSetHashFunctionSeed((uint8_t*)hashseed);
//检查进程参数，是否指定开启哨兵模式
server.sentinel_mode = checkForSentinelMode(argc,argv);
/* 初始化server各种配置项到全局变量struct redisServer server中,这个结构体在server.h中定义，包含了redis的各种配置 */
initServerConfig();
//初始化各种模块库名
moduleInitModulesSystem();
/* Store the executable path and arguments in a safe place in order
* to be able to restart the server later. */
//填充redis-server全路径，后面重启用
server.executable = getAbsolutePath(argv[0]);
server.exec_argv = zmalloc(sizeof(char*)*(argc+1));
server.exec_argv[argc] = NULL;
for (j = 0; j < argc; j++) server.exec_argv[j] = zstrdup(argv[j]);
/* We need to init sentinel right now as parsing the configuration file
* in sentinel mode will have the effect of populating the sentinel
* data structures with master nodes to monitor. */
if (server.sentinel_mode) {
//初始化哨兵模式配置
initSentinelConfig();
initSentinel();
}
/* Check if we need to start in redis-check-rdb/aof mode. We just execute
* the program main. However the program is part of the Redis executable
* so that we can easily execute an RDB check on loading errors. */
//初始化redis的持久化方案，使用rdb或者aof,默认rdb.
if (strstr(argv[0],"redis-check-rdb") != NULL)
redis_check_rdb_main(argc,argv,NULL);
else if (strstr(argv[0],"redis-check-aof") != NULL)
redis_check_aof_main(argc,argv);
if (argc >= 2) {
j = 1; /* First option to parse in argv[] */
sds options = sdsempty();
char *configfile = NULL;
//解析帮助参数
/* Handle special options --help and --version */
if (strcmp(argv[1], "-v") == 0 ||
strcmp(argv[1], "--version") == 0) version();
if (strcmp(argv[1], "--help") == 0 ||
strcmp(argv[1], "-h") == 0) usage();
if (strcmp(argv[1], "--test-memory") == 0) {
...
}
/* First argument is the config file name? */
//解析redis.conf文件路径
if (argv[j][0] != '-' || argv[j][1] != '-') {
configfile = argv[j];
server.configfile = getAbsolutePath(configfile);
/* Replace the config file in server.exec_argv with
* its absolute path. */
zfree(server.exec_argv[j]);
server.exec_argv[j] = zstrdup(server.configfile);
j++;
}
/* All the other options are parsed and conceptually appended to the
* configuration file. For instance --port 6380 will generate the
* string "port 6380\n" to be parsed after the actual file name
* is parsed, if any. */
while(j != argc) {
if (argv[j][0] == '-' && argv[j][1] == '-') {
/* Option name */
//解析--check-rdb参数
if (!strcmp(argv[j], "--check-rdb")) {
/* Argument has no options, need to skip for parsing. */
j++;
continue;
}
if (sdslen(options)) options = sdscat(options,"\n");
options = sdscat(options,argv[j]+2);
options = sdscat(options," ");
} else {
/* Option argument */
options = sdscatrepr(options,argv[j],strlen(argv[j]));
options = sdscat(options," ");
}
j++;
}
if (server.sentinel_mode && configfile && *configfile == '-') {
serverLog(LL_WARNING,
"Sentinel config from STDIN not allowed.");
serverLog(LL_WARNING,
"Sentinel needs config file on disk to save state. Exiting...");
exit(1);
}
resetServerSaveParams();
// 解析redis.conf文件到struct redisServer server对象里面.
loadServerConfig(configfile,options);
sdsfree(options);
}
//打印redis启动时的提示语
serverLog(LL_WARNING, "oO0OoO0OoO0Oo Redis is starting oO0OoO0OoO0Oo");
serverLog(LL_WARNING,
"Redis version=%s, bits=%d, commit=%s, modified=%d, pid=%d, just started",
REDIS_VERSION,
(sizeof(long) == 8) ? 64 : 32,
redisGitSHA1(),
strtol(redisGitDirty(),NULL,10) > 0,
(int)getpid());
if (argc == 1) {
serverLog(LL_WARNING, "Warning: no config file specified, using the default config. In order to specify a config file use %s /path/to/%s.conf", argv[0], server.sentinel_mode ? "sentinel" : "redis");
} else {
serverLog(LL_WARNING, "Configuration loaded");
}
//使用supervise监控进程的重启,僵死等
server.supervised = redisIsSupervised(server.supervised_mode);
int background = server.daemonize && !server.supervised;
if (background) daemonize();
/*初始化创建redis的pid,当前客户端列表,主从列表等.初始化struct sharedObjectsStruct shared对象.
注册文件，客户端事件事件处理方法acceptTcpHandler,lua脚本命令 */
initServer();
if (background || server.pidfile)
//创建pid文件
createPidFile();
//根据redis是哨兵还是集群模式设置进程名
redisSetProcTitle(argv[0]);
//打印redis启动的欢迎图案
redisAsciiArt();
checkTcpBacklogSettings();
if (!server.sentinel_mode) {
/* Things not needed when running in Sentinel mode. */
serverLog(LL_WARNING,"Server initialized");
#ifdef __linux__
linuxMemoryWarnings();
#endif
//动态加载前面的so库
moduleLoadFromQueue();
//使用AOF或者RDB模式从磁盘文件中加载数据
loadDataFromDisk();
if (server.cluster_enabled) {
if (verifyClusterConfigWithData() == C_ERR) {
serverLog(LL_WARNING,
"You can't have keys in a DB different than DB 0 when in "
"Cluster mode. Exiting.");
exit(1);
}
}
if (server.ipfd_count > 0)
serverLog(LL_NOTICE,"Ready to accept connections");
if (server.sofd > 0)
serverLog(LL_NOTICE,"The server is now ready to accept connections at %s", server.unixsocket);
} else {
sentinelIsRunning();
}
/* Warning the user about suspicious maxmemory setting. */
if (server.maxmemory > 0 && server.maxmemory < 1024*1024) {
serverLog(LL_WARNING,"WARNING: You specified a maxmemory value that is less than 1MB (current value is %llu bytes). Are you sure this is what you really want?", server.maxmemory);
}
aeSetBeforeSleepProc(server.el,beforeSleep);
aeSetAfterSleepProc(server.el,afterSleep);
/* 开启redis自己的ae事件模型，接收客户端网络请求,支持epoll、select、kqueue、以及基于Solaris的event ports.代码在二处分析*/
aeMain(server.el);
aeDeleteEventLoop(server.el);
return 0;
}
入口在server.c文件中的main()方法中.
主要代码如上面注释。几个关键环节处理如下：
(一).如果是哨兵模式,进入initSentinel()
1.调用dictEmpty清空redisServer.commands命令路由表.赋值只接受sentinelcmds里面的ping、sentinel、info、subscribe等几个命令.
(二).initServer().
1.初始化redisServer server和struct sharedObjectsStruct shared共享对象.
初始化server的aeEventLoop对象，监听6379端口.
2.调用clientsCron创建客户端相关的各种后台任务，调用databasesCron()创建aof或者rdb的后台同步任务.调用rewriteAppendOnlyFileBackground重写aof文件.rdb任务执行完后回调backgroundSaveDoneHandler方法.aof任务完成后回调backgroundRewriteDoneHandler方法.调用rdbSaveBackground和rewriteAppendOnlyFileBackground启动后台rdb或aof任务.
3.启动replicationCron主从监控，clusterCron集群监控(集群模式),sentinelTimer(哨兵模式)的后台任务.
4.注册acceptTcpHandler为监听套接字的处理方法，处理客户端连接和命令都在这个方法。
5.调用scriptingInit()初始化lua脚本库.注册lua命令表,创建lua支持的命令.
(三).loadDataFromDisk
从磁盘加载数据缓存文件.
(三.一)如果是aof，进入loadAppendOnlyFile(),如果是rdb,进入rdbLoad(),默认是aof优先加载.默认持久化方式是rdb。进入rdbLoad().
1.fopen打开rdb文件,设置加载的进度回调方法rdbLoadProgressCallback.先读取9个字节，判断是不是"REDIS"字串.再读取5个字节版本号，看是不是在1和6之间。然后while死循环读取文件内容。
2.每次循环依次读取每个缓存key,1个字节的type,4个字节的过期时间，key(1个字节的编码类型，对应类型的key的长度)，value,然后把key和value写入redis进程，增加key的计数.编码类型有REDIS_RDB_ENC_INT8，REDIS_RDB_ENC_INT16，REDIS_RDB_ENC_INT32，REDIS_RDB_ENC_LZF四种.调用dbAdd()方法添加key和value到redis的db中.
(三.二).aof方式加载数据文件,进入loadAppendOnlyFile().
1.fopen打开日志文件,调用createFakeClient(),创建一个假的redisClient.死循环读取日志文件中的命令，每1000个命令回调一次进度回调方法。每次循环依次读取每个命令，先读取128个字节,再读取1个字节的计数器，代表这次的命令个数。每个命令，先读取1个字节的长度，然后读取该长度代表的命令内容，调用lookupCommand()读取该命令对应的缓存key的value,调用该命令的redisCommandProc方法执行该命令.
二.redis的IO模型
处理io模型,代码如下,先放这，后面有时间再分析:
/* Process every pending time event, then every pending file event
* (that may be registered by time event callbacks just processed).
* Without special flags the function sleeps until some file event
* fires, or when the next time event occurs (if any).
*
* If flags is 0, the function does nothing and returns.
* if flags has AE_ALL_EVENTS set, all the kind of events are processed.
* if flags has AE_FILE_EVENTS set, file events are processed.
* if flags has AE_TIME_EVENTS set, time events are processed.
* if flags has AE_DONT_WAIT set the function returns ASAP until all
* if flags has AE_CALL_AFTER_SLEEP set, the aftersleep callback is called.
* the events that's possible to process without to wait are processed.
*
* The function returns the number of events processed. */
int aeProcessEvents(aeEventLoop *eventLoop, int flags)
{
int processed = 0, numevents;
/* Nothing to do? return ASAP */
//没有IO事件，直接返回
if (!(flags & AE_TIME_EVENTS) && !(flags & AE_FILE_EVENTS)) return 0;
/* Note that we want call select() even if there are no
* file events to process as long as we want to process time
* events, in order to sleep until the next time event is ready
* to fire. */
if (eventLoop->maxfd != -1 ||
((flags & AE_TIME_EVENTS) && !(flags & AE_DONT_WAIT))) {
int j;
aeTimeEvent *shortest = NULL;
struct timeval tv, *tvp;
if (flags & AE_TIME_EVENTS && !(flags & AE_DONT_WAIT))
shortest = aeSearchNearestTimer(eventLoop);
if (shortest) {
long now_sec, now_ms;
aeGetTime(&now_sec, &now_ms);
tvp = &tv;
/* How many milliseconds we need to wait for the next
* time event to fire? */
long long ms =
(shortest->when_sec - now_sec)*1000 +
shortest->when_ms - now_ms;
if (ms > 0) {
tvp->tv_sec = ms/1000;
tvp->tv_usec = (ms % 1000)*1000;
} else {
tvp->tv_sec = 0;
tvp->tv_usec = 0;
}
} else {
/* If we have to check for events but need to return
* ASAP because of AE_DONT_WAIT we need to set the timeout
* to zero */
if (flags & AE_DONT_WAIT) {
tv.tv_sec = tv.tv_usec = 0;
tvp = &tv;
} else {
/* Otherwise we can block */
tvp = NULL; /* wait forever */
}
}
/* Call the multiplexing API, will return only on timeout or when
* some event fires. */
numevents = aeApiPoll(eventLoop, tvp);
/* After sleep callback. */
if (eventLoop->aftersleep != NULL && flags & AE_CALL_AFTER_SLEEP)
eventLoop->aftersleep(eventLoop);
for (j = 0; j < numevents; j++) {
aeFileEvent *fe = &eventLoop->events[eventLoop->fired[j].fd];
int mask = eventLoop->fired[j].mask;
int fd = eventLoop->fired[j].fd;
int fired = 0; /* Number of events fired for current fd. */
/* Normally we execute the readable event first, and the writable
* event laster. This is useful as sometimes we may be able
* to serve the reply of a query immediately after processing the
* query.
*
* However if AE_BARRIER is set in the mask, our application is
* asking us to do the reverse: never fire the writable event
* after the readable. In such a case, we invert the calls.
* This is useful when, for instance, we want to do things
* in the beforeSleep() hook, like fsynching a file to disk,
* before replying to a client. */
int invert = fe->mask & AE_BARRIER;
/* Note the "fe->mask & mask & ..." code: maybe an already
* processed event removed an element that fired and we still
* didn't processed, so we check if the event is still valid.
*
* Fire the readable event if the call sequence is not
* inverted. */
if (!invert && fe->mask & mask & AE_READABLE) {
fe->rfileProc(eventLoop,fd,fe->clientData,mask);
fired++;
}
/* Fire the writable event. */
if (fe->mask & mask & AE_WRITABLE) {
if (!fired || fe->wfileProc != fe->rfileProc) {
fe->wfileProc(eventLoop,fd,fe->clientData,mask);
fired++;
}
}
/* If we have to invert the call, fire the readable event now
* after the writable one. */
if (invert && fe->mask & mask & AE_READABLE) {
if (!fired || fe->wfileProc != fe->rfileProc) {
fe->rfileProc(eventLoop,fd,fe->clientData,mask);
fired++;
}
}
processed++;
}
}
/* Check time events */
if (flags & AE_TIME_EVENTS)
processed += processTimeEvents(eventLoop);
return processed; /* return the number of processed file/time events */
}三.客户端请求处理过程
进入acceptTcpHandler方法，这个是在redis启动时，initServer()方法里面注册的。
1.文件事件,网络事件也为文件事件,处理方法为networking.c文件中的acceptTcpHandler()方法.
acceptTcpHandler方法在redis启动时在initServer()方法中注册为文件事件处理回调函数.代码如下:
void acceptTcpHandler(aeEventLoop *el, int fd, void *privdata, int mask)
{
int cport, cfd, max = MAX_ACCEPTS_PER_CALL;
char cip[NET_IP_STR_LEN];
UNUSED(el);
UNUSED(mask);
UNUSED(privdata);
while(max--) {
//接收网络连接
cfd = anetTcpAccept(server.neterr, fd, cip, sizeof(cip), &cport);
if (cfd == ANET_ERR) {
if (errno != EWOULDBLOCK)
serverLog(LL_WARNING,
"Accepting client connection: %s", server.neterr);
return;
}
serverLog(LL_VERBOSE,"Accepted %s:%d", cip, cport);
//处理连接请求,代码在后面2处分析
acceptCommonHandler(cfd,0,cip);
}
}2.处理请求方法,代码如下:
networking.c中的acceptCommonHandler()方法.
#define MAX_ACCEPTS_PER_CALL 1000
static void acceptCommonHandler(int fd, int flags, char *ip) {
client *c;
/* 每个连接请求创建一个client结构处理.在这个方法里面注册readQueryFromClient()方法为处理客户端请求,代码在后面3处分析 */
if ((c = createClient(fd)) == NULL) {
serverLog(LL_WARNING,
"Error registering fd event for the new client: %s (fd=%d)",
strerror(errno),fd);
close(fd); /* May be already closed, just ignore errors */
return;
}
/* If maxclient directive is set and this is one client more... close the
* connection. Note that we create the client instead to check before
* for this condition, since now the socket is already set in non-blocking
* mode and we can send an error for free using the Kernel I/O */
//达到客户端连接个数最大值，返回错误
if (listLength(server.clients) > server.maxclients) {
char *err = "-ERR max number of clients reached\r\n";
/* That's a best effort error message, don't check write errors */
if (write(c->fd,err,strlen(err)) == -1) {
/* Nothing to do, Just to avoid the warning... */
}
server.stat_rejected_conn++;
freeClient(c);
return;
}
/* If the server is running in protected mode (the default) and there
* is no password set, nor a specific interface is bound, we don't accept
* requests from non loopback interfaces. Instead we try to explain the
* user what to do to fix it if needed. */
if (server.protected_mode &&
server.bindaddr_count == 0 &&
server.requirepass == NULL &&
!(flags & CLIENT_UNIX_SOCKET) &&
ip != NULL)
{
xxx
}
server.stat_numconnections++;
c->flags |= flags;
}3.读取客户请求
在createClient()方法中进入networking.c文件中的readQueryFromClient()方法.
void readQueryFromClient(aeEventLoop *el, int fd, void *privdata, int mask) {
client *c = (client*) privdata;
int nread, readlen;
size_t qblen;
UNUSED(el);
UNUSED(mask);
readlen = PROTO_IOBUF_LEN;
/* If this is a multi bulk request, and we are processing a bulk reply
* that is large enough, try to maximize the probability that the query
* buffer contains exactly the SDS string representing the object, even
* at the risk of requiring more read(2) calls. This way the function
* processMultiBulkBuffer() can avoid copying buffers to create the
* Redis Object representing the argument. */
//判断是是不是多次请求拿到数据
if (c->reqtype == PROTO_REQ_MULTIBULK && c->multibulklen && c->bulklen != -1
&& c->bulklen >= PROTO_MBULK_BIG_ARG)
{
ssize_t remaining = (size_t)(c->bulklen+2)-sdslen(c->querybuf);
/* Note that the 'remaining' variable may be zero in some edge case,
* for example once we resume a blocked client after CLIENT PAUSE. */
if (remaining > 0 && remaining < readlen) readlen = remaining;
}
qblen = sdslen(c->querybuf);
if (c->querybuf_peak < qblen) c->querybuf_peak = qblen;
c->querybuf = sdsMakeRoomFor(c->querybuf, readlen);
/* 读取用户数据到类型为sds的Client.querybuf中.sds是redis自定义的字符串表示方式.字串内容为请求的字符串,比如get xxx*/
nread = read(fd, c->querybuf+qblen, readlen);
if (nread == -1) {
if (errno == EAGAIN) {
return;
} else {
serverLog(LL_VERBOSE, "Reading from client: %s",strerror(errno));
freeClient(c);
return;
}
} else if (nread == 0) {
serverLog(LL_VERBOSE, "Client closed connection");
freeClient(c);
return;
} else if (c->flags & CLIENT_MASTER) {
/* Append the query buffer to the pending (not applied) buffer
* of the master. We'll use this buffer later in order to have a
* copy of the string applied by the last command executed. */
c->pending_querybuf = sdscatlen(c->pending_querybuf,
c->querybuf+qblen,nread);
}
sdsIncrLen(c->querybuf,nread);
c->lastinteraction = server.unixtime;
if (c->flags & CLIENT_MASTER) c->read_reploff += nread;
server.stat_net_input_bytes += nread;
if (sdslen(c->querybuf) > server.client_max_querybuf_len) {
sds ci = catClientInfoString(sdsempty(),c), bytes = sdsempty();
bytes = sdscatrepr(bytes,c->querybuf,64);
serverLog(LL_WARNING,"Closing client that reached max query buffer length: %s (qbuf initial bytes: %s)", ci, bytes);
sdsfree(ci);
sdsfree(bytes);
freeClient(c);
return;
}
/* Time to process the buffer. If the client is a master we need to
* compute the difference between the applied offset before and after
* processing the buffer, to understand how much of the replication stream
* was actually applied to the master state: this quantity, and its
* corresponding part of the replication stream, will be propagated to
* the sub-slaves and to the replication backlog. */
/* 处理用户请求的命令,依次调用networking.c文件中的processInputBuffer()--> server.c文件中的processCommand()方法,
代码在后面4处分析*/
processInputBufferAndReplicate(c);
}4.处理客户命令
在processInputBufferAndReplicate()方法中进入server.c文件中的processCommand()方法,使用命令模式,代码如下:
/* If this function gets called we already read a whole
* command, arguments are in the client argv/argc fields.
* processCommand() execute the command or prepare the
* server for a bulk read from the client.
*
* If C_OK is returned the client is still alive and valid and
* other operations can be performed by the caller. Otherwise
* if C_ERR is returned the client was destroyed (i.e. after QUIT). */
int processCommand(client *c) {
/* The QUIT command is handled separately. Normal command procs will
* go through checking for replication and QUIT will cause trouble
* when FORCE_REPLICATION is enabled and would be implemented in
* a regular command proc. */
//处理quit命令,addReply()方法是向用户发包
if (!strcasecmp(c->argv[0]->ptr,"quit")) {
addReply(c,shared.ok);
c->flags |= CLIENT_CLOSE_AFTER_REPLY;
return C_ERR;
}
/* Now lookup the command and check ASAP about trivial error conditions
* such as wrong arity, bad command name and so forth. */
/*遍历命令列表,匹配时哪个命令，所有的命令是redis刚启动时填充到 server.c文件中的redisCommandTable全局变量中的，在后面代码5
处展示*/
c->cmd = c->lastcmd = lookupCommand(c->argv[0]->ptr);
if (!c->cmd) {
flagTransaction(c);
sds args = sdsempty();
int i;
for (i=1; i < c->argc && sdslen(args) < 128; i++)
args = sdscatprintf(args, "`%.*s`, ", 128-(int)sdslen(args), (char*)c->argv[i]->ptr);
addReplyErrorFormat(c,"unknown command `%s`, with args beginning with: %s",
(char*)c->argv[0]->ptr, args);
sdsfree(args);
return C_OK;
} else if ((c->cmd->arity > 0 && c->cmd->arity != c->argc) ||
(c->argc < -c->cmd->arity)) {
flagTransaction(c);
addReplyErrorFormat(c,"wrong number of arguments for '%s' command",
c->cmd->name);
return C_OK;
}
/* Check if the user is authenticated */
//查看客户是否有权限执行命令
if (server.requirepass && !c->authenticated && c->cmd->proc != authCommand)
{
flagTransaction(c);
addReply(c,shared.noautherr);
return C_OK;
}
/* If cluster is enabled perform the cluster redirection here.
* However we don't perform the redirection if:
* 1) The sender of this command is our master.
* 2) The command has no key arguments. */
//集群处理
if (server.cluster_enabled &&
!(c->flags & CLIENT_MASTER) &&
!(c->flags & CLIENT_LUA &&
server.lua_caller->flags & CLIENT_MASTER) &&
!(c->cmd->getkeys_proc == NULL && c->cmd->firstkey == 0 &&
c->cmd->proc != execCommand))
{
int hashslot;
int error_code;
clusterNode *n = getNodeByQuery(c,c->cmd,c->argv,c->argc,
&hashslot,&error_code);
if (n == NULL || n != server.cluster->myself) {
if (c->cmd->proc == execCommand) {
discardTransaction(c);
} else {
flagTransaction(c);
}
clusterRedirectClient(c,n,hashslot,error_code);
return C_OK;
}
}
/* Handle the maxmemory directive.
*
* First we try to free some memory if possible (if there are volatile
* keys in the dataset). If there are not the only thing we can do
* is returning an error.
*
* Note that we do not want to reclaim memory if we are here re-entering
* the event loop since there is a busy Lua script running in timeout
* condition, to avoid mixing the propagation of scripts with the propagation
* of DELs due to eviction. */
//服务端内存不够用处理,oom
if (server.maxmemory && !server.lua_timedout) {
int out_of_memory = freeMemoryIfNeeded() == C_ERR;
/* freeMemoryIfNeeded may flush slave output buffers. This may result
* into a slave, that may be the active client, to be freed. */
if (server.current_client == NULL) return C_ERR;
/* It was impossible to free enough memory, and the command the client
* is trying to execute is denied during OOM conditions? Error. */
if ((c->cmd->flags & CMD_DENYOOM) && out_of_memory) {
flagTransaction(c);
addReply(c, shared.oomerr);
return C_OK;
}
}
/* Don't accept write commands if there are problems persisting on disk
* and if this is a master instance. */
//写磁盘错误
int deny_write_type = writeCommandsDeniedByDiskError();
if (deny_write_type != DISK_ERROR_TYPE_NONE &&
server.masterhost == NULL &&
(c->cmd->flags & CMD_WRITE ||
c->cmd->proc == pingCommand))
{
flagTransaction(c);
if (deny_write_type == DISK_ERROR_TYPE_RDB)
addReply(c, shared.bgsaveerr);
else
addReplySds(c,
sdscatprintf(sdsempty(),
"-MISCONF Errors writing to the AOF file: %s\r\n",
strerror(server.aof_last_write_errno)));
return C_OK;
}
/* Don't accept write commands if there are not enough good slaves and
* user configured the min-slaves-to-write option. */
if (server.masterhost == NULL &&
server.repl_min_slaves_to_write &&
server.repl_min_slaves_max_lag &&
c->cmd->flags & CMD_WRITE &&
server.repl_good_slaves_count < server.repl_min_slaves_to_write)
{
flagTransaction(c);
addReply(c, shared.noreplicaserr);
return C_OK;
}
...
/* Lua script too slow? Only allow a limited number of commands. */
if (server.lua_timedout &&
c->cmd->proc != authCommand &&
c->cmd->proc != replconfCommand &&
!(c->cmd->proc == shutdownCommand &&
c->argc == 2 &&
tolower(((char*)c->argv[1]->ptr)[0]) == 'n') &&
!(c->cmd->proc == scriptCommand &&
c->argc == 2 &&
tolower(((char*)c->argv[1]->ptr)[0]) == 'k'))
{
flagTransaction(c);
addReply(c, shared.slowscripterr);
return C_OK;
}
/* Exec the command */
if (c->flags & CLIENT_MULTI &&
c->cmd->proc != execCommand && c->cmd->proc != discardCommand &&
c->cmd->proc != multiCommand && c->cmd->proc != watchCommand)
{
queueMultiCommand(c);
addReply(c,shared.queued);
} else {
//执行命令,进入,如果是get命令，进入getCommand()方法执行，代码在后面6处分析
call(c,CMD_CALL_FULL);
c->woff = server.master_repl_offset;
if (listLength(server.ready_keys))
handleClientsBlockedOnKeys();
}
return C_OK;
}5.redis命令列表处理方法,每个命令在这里面找处理函数
struct redisCommand redisCommandTable[] = {
{"module",moduleCommand,-2,"as",0,NULL,0,0,0,0,0},
/*getCommand是get命令的处理函数，在t_string.c文件中的getCommand()方法里面,代码在后面6处分析.*/
{"get",getCommand,2,"rF",0,NULL,1,1,1,0,0},
{"set",setCommand,-3,"wm",0,NULL,1,1,1,0,0},
{"setnx",setnxCommand,3,"wmF",0,NULL,1,1,1,0,0},
{"setex",setexCommand,4,"wm",0,NULL,1,1,1,0,0},
{"psetex",psetexCommand,4,"wm",0,NULL,1,1,1,0,0},
{"append",appendCommand,3,"wm",0,NULL,1,1,1,0,0},
{"strlen",strlenCommand,2,"rF",0,NULL,1,1,1,0,0},
{"del",delCommand,-2,"w",0,NULL,1,-1,1,0,0},
{"unlink",unlinkCommand,-2,"wF",0,NULL,1,-1,1,0,0},
{"exists",existsCommand,-2,"rF",0,NULL,1,-1,1,0,0},
{"setbit",setbitCommand,4,"wm",0,NULL,1,1,1,0,0},
{"getbit",getbitCommand,3,"rF",0,NULL,1,1,1,0,0},
{"bitfield",bitfieldCommand,-2,"wm",0,NULL,1,1,1,0,0},
{"setrange",setrangeCommand,4,"wm",0,NULL,1,1,1,0,0},
{"getrange",getrangeCommand,4,"r",0,NULL,1,1,1,0,0},
{"substr",getrangeCommand,4,"r",0,NULL,1,1,1,0,0},
{"incr",incrCommand,2,"wmF",0,NULL,1,1,1,0,0},
{"decr",decrCommand,2,"wmF",0,NULL,1,1,1,0,0},
{"mget",mgetCommand,-2,"rF",0,NULL,1,-1,1,0,0},
{"rpush",rpushCommand,-3,"wmF",0,NULL,1,1,1,0,0},
{"lpush",lpushCommand,-3,"wmF",0,NULL,1,1,1,0,0},
{"rpushx",rpushxCommand,-3,"wmF",0,NULL,1,1,1,0,0},
{"lpushx",lpushxCommand,-3,"wmF",0,NULL,1,1,1,0,0},
{"linsert",linsertCommand,5,"wm",0,NULL,1,1,1,0,0},
{"rpop",rpopCommand,2,"wF",0,NULL,1,1,1,0,0},
{"lpop",lpopCommand,2,"wF",0,NULL,1,1,1,0,0},
{"brpop",brpopCommand,-3,"ws",0,NULL,1,-2,1,0,0},
{"brpoplpush",brpoplpushCommand,4,"wms",0,NULL,1,2,1,0,0},
{"blpop",blpopCommand,-3,"ws",0,NULL,1,-2,1,0,0},
{"llen",llenCommand,2,"rF",0,NULL,1,1,1,0,0},
{"lindex",lindexCommand,3,"r",0,NULL,1,1,1,0,0},
{"lset",lsetCommand,4,"wm",0,NULL,1,1,1,0,0},
{"lrange",lrangeCommand,4,"r",0,NULL,1,1,1,0,0},
{"ltrim",ltrimCommand,4,"w",0,NULL,1,1,1,0,0},
{"lrem",lremCommand,4,"w",0,NULL,1,1,1,0,0},
{"rpoplpush",rpoplpushCommand,3,"wm",0,NULL,1,2,1,0,0},
{"sadd",saddCommand,-3,"wmF",0,NULL,1,1,1,0,0},
{"srem",sremCommand,-3,"wF",0,NULL,1,1,1,0,0},
{"smove",smoveCommand,4,"wF",0,NULL,1,2,1,0,0},
{"sismember",sismemberCommand,3,"rF",0,NULL,1,1,1,0,0},
{"scard",scardCommand,2,"rF",0,NULL,1,1,1,0,0},
{"spop",spopCommand,-2,"wRF",0,NULL,1,1,1,0,0},
{"srandmember",srandmemberCommand,-2,"rR",0,NULL,1,1,1,0,0},
{"sinter",sinterCommand,-2,"rS",0,NULL,1,-1,1,0,0},
{"sinterstore",sinterstoreCommand,-3,"wm",0,NULL,1,-1,1,0,0},
{"sunion",sunionCommand,-2,"rS",0,NULL,1,-1,1,0,0},
{"sunionstore",sunionstoreCommand,-3,"wm",0,NULL,1,-1,1,0,0},
{"sdiff",sdiffCommand,-2,"rS",0,NULL,1,-1,1,0,0},
{"sdiffstore",sdiffstoreCommand,-3,"wm",0,NULL,1,-1,1,0,0},
{"smembers",sinterCommand,2,"rS",0,NULL,1,1,1,0,0},
{"sscan",sscanCommand,-3,"rR",0,NULL,1,1,1,0,0},
{"zadd",zaddCommand,-4,"wmF",0,NULL,1,1,1,0,0},
{"zincrby",zincrbyCommand,4,"wmF",0,NULL,1,1,1,0,0},
{"zrem",zremCommand,-3,"wF",0,NULL,1,1,1,0,0},
{"zremrangebyscore",zremrangebyscoreCommand,4,"w",0,NULL,1,1,1,0,0},
{"zremrangebyrank",zremrangebyrankCommand,4,"w",0,NULL,1,1,1,0,0},
{"zremrangebylex",zremrangebylexCommand,4,"w",0,NULL,1,1,1,0,0},
{"zunionstore",zunionstoreCommand,-4,"wm",0,zunionInterGetKeys,0,0,0,0,0},
{"zinterstore",zinterstoreCommand,-4,"wm",0,zunionInterGetKeys,0,0,0,0,0},
{"zrange",zrangeCommand,-4,"r",0,NULL,1,1,1,0,0},
{"zrangebyscore",zrangebyscoreCommand,-4,"r",0,NULL,1,1,1,0,0},
{"zrevrangebyscore",zrevrangebyscoreCommand,-4,"r",0,NULL,1,1,1,0,0},
{"zrangebylex",zrangebylexCommand,-4,"r",0,NULL,1,1,1,0,0},
{"zrevrangebylex",zrevrangebylexCommand,-4,"r",0,NULL,1,1,1,0,0},
{"zcount",zcountCommand,4,"rF",0,NULL,1,1,1,0,0},
{"zlexcount",zlexcountCommand,4,"rF",0,NULL,1,1,1,0,0},
{"zrevrange",zrevrangeCommand,-4,"r",0,NULL,1,1,1,0,0},
{"zcard",zcardCommand,2,"rF",0,NULL,1,1,1,0,0},
{"zscore",zscoreCommand,3,"rF",0,NULL,1,1,1,0,0},
{"zrank",zrankCommand,3,"rF",0,NULL,1,1,1,0,0},
{"zrevrank",zrevrankCommand,3,"rF",0,NULL,1,1,1,0,0},
{"zscan",zscanCommand,-3,"rR",0,NULL,1,1,1,0,0},
{"zpopmin",zpopminCommand,-2,"wF",0,NULL,1,1,1,0,0},
{"zpopmax",zpopmaxCommand,-2,"wF",0,NULL,1,1,1,0,0},
{"bzpopmin",bzpopminCommand,-2,"wsF",0,NULL,1,-2,1,0,0},
{"bzpopmax",bzpopmaxCommand,-2,"wsF",0,NULL,1,-2,1,0,0},
{"hset",hsetCommand,-4,"wmF",0,NULL,1,1,1,0,0},
{"hsetnx",hsetnxCommand,4,"wmF",0,NULL,1,1,1,0,0},
{"hget",hgetCommand,3,"rF",0,NULL,1,1,1,0,0},
{"hmset",hsetCommand,-4,"wmF",0,NULL,1,1,1,0,0},
{"hmget",hmgetCommand,-3,"rF",0,NULL,1,1,1,0,0},
{"hincrby",hincrbyCommand,4,"wmF",0,NULL,1,1,1,0,0},
{"hincrbyfloat",hincrbyfloatCommand,4,"wmF",0,NULL,1,1,1,0,0},
{"hdel",hdelCommand,-3,"wF",0,NULL,1,1,1,0,0},
{"hlen",hlenCommand,2,"rF",0,NULL,1,1,1,0,0},
{"hstrlen",hstrlenCommand,3,"rF",0,NULL,1,1,1,0,0},
{"hkeys",hkeysCommand,2,"rS",0,NULL,1,1,1,0,0},
{"hvals",hvalsCommand,2,"rS",0,NULL,1,1,1,0,0},
{"hgetall",hgetallCommand,2,"rR",0,NULL,1,1,1,0,0},
{"hexists",hexistsCommand,3,"rF",0,NULL,1,1,1,0,0},
{"hscan",hscanCommand,-3,"rR",0,NULL,1,1,1,0,0},
{"incrby",incrbyCommand,3,"wmF",0,NULL,1,1,1,0,0},
{"decrby",decrbyCommand,3,"wmF",0,NULL,1,1,1,0,0},
{"incrbyfloat",incrbyfloatCommand,3,"wmF",0,NULL,1,1,1,0,0},
{"getset",getsetCommand,3,"wm",0,NULL,1,1,1,0,0},
{"mset",msetCommand,-3,"wm",0,NULL,1,-1,2,0,0},
{"msetnx",msetnxCommand,-3,"wm",0,NULL,1,-1,2,0,0},
{"randomkey",randomkeyCommand,1,"rR",0,NULL,0,0,0,0,0},
{"select",selectCommand,2,"lF",0,NULL,0,0,0,0,0},
{"swapdb",swapdbCommand,3,"wF",0,NULL,0,0,0,0,0},
{"move",moveCommand,3,"wF",0,NULL,1,1,1,0,0},
{"rename",renameCommand,3,"w",0,NULL,1,2,1,0,0},
{"renamenx",renamenxCommand,3,"wF",0,NULL,1,2,1,0,0},
{"expire",expireCommand,3,"wF",0,NULL,1,1,1,0,0},
{"expireat",expireatCommand,3,"wF",0,NULL,1,1,1,0,0},
{"pexpire",pexpireCommand,3,"wF",0,NULL,1,1,1,0,0},
{"pexpireat",pexpireatCommand,3,"wF",0,NULL,1,1,1,0,0},
{"keys",keysCommand,2,"rS",0,NULL,0,0,0,0,0},
{"scan",scanCommand,-2,"rR",0,NULL,0,0,0,0,0},
{"dbsize",dbsizeCommand,1,"rF",0,NULL,0,0,0,0,0},
{"auth",authCommand,2,"sltF",0,NULL,0,0,0,0,0},
{"ping",pingCommand,-1,"tF",0,NULL,0,0,0,0,0},
{"echo",echoCommand,2,"F",0,NULL,0,0,0,0,0},
{"save",saveCommand,1,"as",0,NULL,0,0,0,0,0},
{"bgsave",bgsaveCommand,-1,"as",0,NULL,0,0,0,0,0},
{"bgrewriteaof",bgrewriteaofCommand,1,"as",0,NULL,0,0,0,0,0},
{"shutdown",shutdownCommand,-1,"aslt",0,NULL,0,0,0,0,0},
{"lastsave",lastsaveCommand,1,"RF",0,NULL,0,0,0,0,0},
{"type",typeCommand,2,"rF",0,NULL,1,1,1,0,0},
{"multi",multiCommand,1,"sF",0,NULL,0,0,0,0,0},
{"exec",execCommand,1,"sM",0,NULL,0,0,0,0,0},
{"discard",discardCommand,1,"sF",0,NULL,0,0,0,0,0},
{"sync",syncCommand,1,"ars",0,NULL,0,0,0,0,0},
{"psync",syncCommand,3,"ars",0,NULL,0,0,0,0,0},
{"replconf",replconfCommand,-1,"aslt",0,NULL,0,0,0,0,0},
{"flushdb",flushdbCommand,-1,"w",0,NULL,0,0,0,0,0},
{"flushall",flushallCommand,-1,"w",0,NULL,0,0,0,0,0},
{"sort",sortCommand,-2,"wm",0,sortGetKeys,1,1,1,0,0},
{"info",infoCommand,-1,"ltR",0,NULL,0,0,0,0,0},
{"monitor",monitorCommand,1,"as",0,NULL,0,0,0,0,0},
{"ttl",ttlCommand,2,"rFR",0,NULL,1,1,1,0,0},
{"touch",touchCommand,-2,"rF",0,NULL,1,1,1,0,0},
{"pttl",pttlCommand,2,"rFR",0,NULL,1,1,1,0,0},
{"persist",persistCommand,2,"wF",0,NULL,1,1,1,0,0},
{"slaveof",replicaofCommand,3,"ast",0,NULL,0,0,0,0,0},
{"replicaof",replicaofCommand,3,"ast",0,NULL,0,0,0,0,0},
{"role",roleCommand,1,"lst",0,NULL,0,0,0,0,0},
{"debug",debugCommand,-2,"as",0,NULL,0,0,0,0,0},
{"config",configCommand,-2,"last",0,NULL,0,0,0,0,0},
{"subscribe",subscribeCommand,-2,"pslt",0,NULL,0,0,0,0,0},
{"unsubscribe",unsubscribeCommand,-1,"pslt",0,NULL,0,0,0,0,0},
{"psubscribe",psubscribeCommand,-2,"pslt",0,NULL,0,0,0,0,0},
{"punsubscribe",punsubscribeCommand,-1,"pslt",0,NULL,0,0,0,0,0},
{"publish",publishCommand,3,"pltF",0,NULL,0,0,0,0,0},
{"pubsub",pubsubCommand,-2,"pltR",0,NULL,0,0,0,0,0},
{"watch",watchCommand,-2,"sF",0,NULL,1,-1,1,0,0},
{"unwatch",unwatchCommand,1,"sF",0,NULL,0,0,0,0,0},
{"cluster",clusterCommand,-2,"a",0,NULL,0,0,0,0,0},
{"restore",restoreCommand,-4,"wm",0,NULL,1,1,1,0,0},
{"restore-asking",restoreCommand,-4,"wmk",0,NULL,1,1,1,0,0},
{"migrate",migrateCommand,-6,"wR",0,migrateGetKeys,0,0,0,0,0},
{"asking",askingCommand,1,"F",0,NULL,0,0,0,0,0},
{"readonly",readonlyCommand,1,"F",0,NULL,0,0,0,0,0},
{"readwrite",readwriteCommand,1,"F",0,NULL,0,0,0,0,0},
{"dump",dumpCommand,2,"rR",0,NULL,1,1,1,0,0},
{"object",objectCommand,-2,"rR",0,NULL,2,2,1,0,0},
{"memory",memoryCommand,-2,"rR",0,NULL,0,0,0,0,0},
{"client",clientCommand,-2,"as",0,NULL,0,0,0,0,0},
{"eval",evalCommand,-3,"s",0,evalGetKeys,0,0,0,0,0},
{"evalsha",evalShaCommand,-3,"s",0,evalGetKeys,0,0,0,0,0},
{"slowlog",slowlogCommand,-2,"aR",0,NULL,0,0,0,0,0},
{"script",scriptCommand,-2,"s",0,NULL,0,0,0,0,0},
{"time",timeCommand,1,"RF",0,NULL,0,0,0,0,0},
{"bitop",bitopCommand,-4,"wm",0,NULL,2,-1,1,0,0},
{"bitcount",bitcountCommand,-2,"r",0,NULL,1,1,1,0,0},
{"bitpos",bitposCommand,-3,"r",0,NULL,1,1,1,0,0},
{"wait",waitCommand,3,"s",0,NULL,0,0,0,0,0},
{"command",commandCommand,0,"ltR",0,NULL,0,0,0,0,0},
{"geoadd",geoaddCommand,-5,"wm",0,NULL,1,1,1,0,0},
{"georadius",georadiusCommand,-6,"w",0,georadiusGetKeys,1,1,1,0,0},
{"georadius_ro",georadiusroCommand,-6,"r",0,georadiusGetKeys,1,1,1,0,0},
{"georadiusbymember",georadiusbymemberCommand,-5,"w",0,georadiusGetKeys,1,1,1,0,0},
{"georadiusbymember_ro",georadiusbymemberroCommand,-5,"r",0,georadiusGetKeys,1,1,1,0,0},
{"geohash",geohashCommand,-2,"r",0,NULL,1,1,1,0,0},
{"geopos",geoposCommand,-2,"r",0,NULL,1,1,1,0,0},
{"geodist",geodistCommand,-4,"r",0,NULL,1,1,1,0,0},
{"pfselftest",pfselftestCommand,1,"a",0,NULL,0,0,0,0,0},
{"pfadd",pfaddCommand,-2,"wmF",0,NULL,1,1,1,0,0},
{"pfcount",pfcountCommand,-2,"r",0,NULL,1,-1,1,0,0},
{"pfmerge",pfmergeCommand,-2,"wm",0,NULL,1,-1,1,0,0},
{"pfdebug",pfdebugCommand,-3,"w",0,NULL,0,0,0,0,0},
{"xadd",xaddCommand,-5,"wmFR",0,NULL,1,1,1,0,0},
{"xrange",xrangeCommand,-4,"r",0,NULL,1,1,1,0,0},
{"xrevrange",xrevrangeCommand,-4,"r",0,NULL,1,1,1,0,0},
{"xlen",xlenCommand,2,"rF",0,NULL,1,1,1,0,0},
{"xread",xreadCommand,-4,"rs",0,xreadGetKeys,1,1,1,0,0},
{"xreadgroup",xreadCommand,-7,"ws",0,xreadGetKeys,1,1,1,0,0},
{"xgroup",xgroupCommand,-2,"wm",0,NULL,2,2,1,0,0},
{"xsetid",xsetidCommand,3,"wmF",0,NULL,1,1,1,0,0},
{"xack",xackCommand,-4,"wF",0,NULL,1,1,1,0,0},
{"xpending",xpendingCommand,-3,"rR",0,NULL,1,1,1,0,0},
{"xclaim",xclaimCommand,-6,"wRF",0,NULL,1,1,1,0,0},
{"xinfo",xinfoCommand,-2,"rR",0,NULL,2,2,1,0,0},
{"xdel",xdelCommand,-3,"wF",0,NULL,1,1,1,0,0},
{"xtrim",xtrimCommand,-2,"wFR",0,NULL,1,1,1,0,0},
{"post",securityWarningCommand,-1,"lt",0,NULL,0,0,0,0,0},
{"host:",securityWarningCommand,-1,"lt",0,NULL,0,0,0,0,0},
{"latency",latencyCommand,-2,"aslt",0,NULL,0,0,0,0,0},
{"lolwut",lolwutCommand,-1,"r",0,NULL,0,0,0,0,0}
};6.get命令处理方法
进入t_string.c文件中的getCommand()->getGenericCommand方法,代码如下:
int getGenericCommand(client *c) {
robj *o;
//查询key的值返回,代码在下面分析
if ((o = lookupKeyReadOrReply(c,c->argv[1],shared.nullbulk)) == NULL)
return C_OK;
if (o->type != OBJ_STRING) {
addReply(c,shared.wrongtypeerr);
return C_ERR;
} else {
addReplyBulk(c,o);
return C_OK;
}
}进入db.c文件中的lookupKeyReadOrReply()->lookupKeyReadWithFlags()方法.
robj *lookupKeyReadWithFlags(redisDb *db, robj *key, int flags) {
robj *val;
//查询key是否过期
if (expireIfNeeded(db,key) == 1) {
/* Key expired. If we are in the context of a master, expireIfNeeded()
* returns 0 only when the key does not exist at all, so it's safe
* to return NULL ASAP. */
if (server.masterhost == NULL) return NULL;
/* However if we are in the context of a slave, expireIfNeeded() will
* not really try to expire the key, it only returns information
* about the "logical" status of the key: key expiring is up to the
* master in order to have a consistent view of master's data set.
*
* However, if the command caller is not the master, and as additional
* safety measure, the command invoked is a read-only command, we can
* safely return NULL here, and provide a more consistent behavior
* to clients accessign expired values in a read-only fashion, that
* will say the key as non existing.
*
* Notably this covers GETs when slaves are used to scale reads. */
if (server.current_client &&
server.current_client != server.master &&
server.current_client->cmd &&
server.current_client->cmd->flags & CMD_READONLY)
{
return NULL;
}
}
//查询key的值,代码在下面分析
val = lookupKey(db,key,flags);
if (val == NULL)
server.stat_keyspace_misses++;
else
server.stat_keyspace_hits++;
return val;
}进入db.c文件中的lookupKey()查询key值
/* Low level key lookup API, not actually called directly from commands
* implementations that should instead rely on lookupKeyRead(),
* lookupKeyWrite() and lookupKeyReadWithFlags(). */
robj *lookupKey(redisDb *db, robj *key, int flags) {
//从字典中查询key,代码在下面分析
dictEntry *de = dictFind(db->dict,key->ptr);
if (de) {
robj *val = dictGetVal(de);
/* Update the access time for the ageing algorithm.
* Don't do it if we have a saving child, as this will trigger
* a copy on write madness. */
if (server.rdb_child_pid == -1 &&
server.aof_child_pid == -1 &&
!(flags & LOOKUP_NOTOUCH))
{
//更新key的访问时间
if (server.maxmemory_policy & MAXMEMORY_FLAG_LFU) {
updateLFU(val);
} else {
val->lru = LRU_CLOCK();
}
}
return val;
} else {
return NULL;
}
}根据key,计算hash位置,查找数组中的value值,具体dict字典存储格式，在后面四.dict字典分析
dictEntry *dictFind(dict *d, const void *key)
{
dictEntry *he;
uint64_t h, idx, table;
if (d->ht[0].used + d->ht[1].used == 0) return NULL; /* dict is empty */
if (dictIsRehashing(d)) _dictRehashStep(d);
//计算key的hash值,在数组中的位置,每种类型都有自己的hashFunction()方法.
h = dictHashKey(d, key);
for (table = 0; table <= 1; table++) {
idx = h & d->ht[table].sizemask;
//取出hash值
he = d->ht[table].table[idx];
while(he) {
//遍历hash位置相同的链表，如果key相同，取出结果返回
if (key==he->key || dictCompareKeys(d, key, he->key))
return he;
he = he->next;
}
if (!dictIsRehashing(d)) return NULL;
}
return NULL;
}默认的hashFunction()方法如下所示:
static unsigned int dictGenHashFunction(const unsigned char *buf, int len) {
unsigned int hash = 5381;
while (len--)
hash = ((hash << 5) + hash) + (*buf++); /* hash * 33 + c */
return hash;
}四.dict字典
用来存储具体get,set的数据
typedef struct dict {
//字典类型
dictType *type;
void *privdata;
//存储时间的两个字典，第二个字典用来rehash
dictht ht[2];
long rehashidx; /* rehashing not in progress if rehashidx == -1 */
unsigned long iterators; /* number of iterators currently running */
} dict;/* This is our hash table structure. Every dictionary has two of this as we
* implement incremental rehashing, for the old to the new table. */
typedef struct dictht {
//存储数组的地址
dictEntry **table;
//数组的大小
unsigned long size;
unsigned long sizemask;
//已经使用大小
unsigned long used;
} dictht;//数组元素的结构
typedef struct dictEntry {
//元素的key
void *key;
//元素的value值
union {
void *val;
uint64_t u64;
int64_t s64;
double d;
} v;
//同一hashcode的下一个key,value对
struct dictEntry *next;
} dictEntry;//字典类型
typedef struct dictType {
uint64_t (*hashFunction)(const void *key);
void *(*keyDup)(void *privdata, const void *key);
void *(*valDup)(void *privdata, const void *obj);
int (*keyCompare)(void *privdata, const void *key1, const void *key2);
void (*keyDestructor)(void *privdata, void *key);
void (*valDestructor)(void *privdata, void *obj);
} dictType;dict从网上截了两张图，说的比较清晰，如下:
编辑
扫一扫
2420
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
