[3]redis 处理命令的过程

663 阅读13分钟

在看它的command处理之前,先说一下redis中C/S交互的流程(不知道怎么用图来表示流程,先码在这里):
0.创建事件循环

    server.el = aeCreateEventLoop(server.maxclients+CONFIG_FDSET_INCR);

1.创建时间事件 serverCron()

if(aeCreateTimeEvent(server.el, 1, serverCron, NULL, NULL) == AE_ERR) {
        serverPanic("Can't create the serverCron time event.");
        exit(1);
    }
  1. 在initServer()中调用aeCreateFileEvent给tcp listen socket注册 acceptTcpHandler 做为rfileProc
  2. 有客户端连接过来时,在aeApiPoll中,listen套接字上来了可读事件,调用其注册的rfileProc,也就是acceptTcpHandler
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.");

  1. 在acceptTcpHandler的处理当中会调用createClient,
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--) {
        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);
        acceptCommonHandler(cfd,0,cip);
    }
}
static void acceptCommonHandler(int fd, int flags, char *ip) {
    client *c;
    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 */
    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;
    }

    省略一些代码

    server.stat_numconnections++;
    c->flags |= flags;
}

它除了分配新的redisClient结构之外,还会调用aeCreateFileEvent为新的fd注册可读事件上的rfileProc: readQueryFromClient()

client *createClient(int fd) {
    client *c = zmalloc(sizeof(client));

    /* passing -1 as fd it is possible to create a non connected client.
     * This is useful since all the commands needs to be executed
     * in the context of a client. When commands are executed in other
     * contexts (for instance a Lua script) we need a non connected client. */
    if (fd != -1) {
        anetNonBlock(NULL,fd);
        anetEnableTcpNoDelay(NULL,fd);
        if (server.tcpkeepalive)
            anetKeepAlive(NULL,fd,server.tcpkeepalive);
        if (aeCreateFileEvent(server.el,fd,AE_READABLE,
            readQueryFromClient, c) == AE_ERR)
        {
            close(fd);
            zfree(c);
            return NULL;
        }
    }

    selectDb(c,0);
    c->id = server.next_client_id++;
    c->fd = fd;
    c->name = NULL;
    c->bufpos = 0;
    c->querybuf = sdsempty();
    c->querybuf_peak = 0;
    c->reqtype = 0;
    c->argc = 0;
    c->argv = NULL;
    c->cmd = c->lastcmd = NULL;
    c->multibulklen = 0;
    c->bulklen = -1;
    c->sentlen = 0;
    c->flags = 0;
    c->ctime = c->lastinteraction = server.unixtime;
    c->authenticated = 0;
    c->replstate = REPL_STATE_NONE;
    c->repl_put_online_on_ack = 0;
    c->reploff = 0;
    c->repl_ack_off = 0;
    c->repl_ack_time = 0;
    c->slave_listening_port = 0;
    c->slave_ip[0] = '\0';
    c->slave_capa = SLAVE_CAPA_NONE;
    c->reply = listCreate();
    c->reply_bytes = 0;
    c->obuf_soft_limit_reached_time = 0;
    listSetFreeMethod(c->reply,decrRefCountVoid);
    listSetDupMethod(c->reply,dupClientReplyValue);
    c->btype = BLOCKED_NONE;
    c->bpop.timeout = 0;
    c->bpop.keys = dictCreate(&setDictType,NULL);
    c->bpop.target = NULL;
    c->bpop.numreplicas = 0;
    c->bpop.reploffset = 0;
    c->woff = 0;
    c->watched_keys = listCreate();
    c->pubsub_channels = dictCreate(&setDictType,NULL);
    c->pubsub_patterns = listCreate();
    c->peerid = NULL;
    listSetFreeMethod(c->pubsub_patterns,decrRefCountVoid);
    listSetMatchMethod(c->pubsub_patterns,listMatchObjects);
    if (fd != -1) listAddNodeTail(server.clients,c);
    initClientMultiState(c);
    return c;
}
  1. 当客户端发过来请求时,aeApiPoll中,client套接字上来了可读事件,调用rfileProc也就是readQueryFromClient读取client的请求 放到clients结构体的querybuf字段,
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. */
    if (c->reqtype == PROTO_REQ_MULTIBULK && c->multibulklen && c->bulklen != -1
        && c->bulklen >= PROTO_MBULK_BIG_ARG)
    {
        int remaining = (unsigned)(c->bulklen+2)-sdslen(c->querybuf);

        if (remaining < readlen) readlen = remaining;
    }

    qblen = sdslen(c->querybuf);
    if (c->querybuf_peak < qblen) c->querybuf_peak = qblen;
    c->querybuf = sdsMakeRoomFor(c->querybuf, readlen);
    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;
    }

    sdsIncrLen(c->querybuf,nread);
    c->lastinteraction = server.unixtime;
    if (c->flags & CLIENT_MASTER) c->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;
    }
    processInputBuffer(c);
}

然后调用processInputBuffer()处理收到的请求内容。

void processInputBuffer(client *c) {
    server.current_client = c;
    /* Keep processing while there is something in the input buffer */
    while(sdslen(c->querybuf)) {
        /* Return if clients are paused. */
        if (!(c->flags & CLIENT_SLAVE) && clientsArePaused()) break;

        /* Immediately abort if the client is in the middle of something. */
        if (c->flags & CLIENT_BLOCKED) break;

        /* CLIENT_CLOSE_AFTER_REPLY closes the connection once the reply is
         * written to the client. Make sure to not let the reply grow after
         * this flag has been set (i.e. don't process more commands).
         *
         * The same applies for clients we want to terminate ASAP. */
        if (c->flags & (CLIENT_CLOSE_AFTER_REPLY|CLIENT_CLOSE_ASAP)) break;

        /* Determine request type when unknown. */
        if (!c->reqtype) {
            if (c->querybuf[0] == '*') {
                c->reqtype = PROTO_REQ_MULTIBULK;
            } else {
                c->reqtype = PROTO_REQ_INLINE;
            }
        }

        if (c->reqtype == PROTO_REQ_INLINE) {
            if (processInlineBuffer(c) != C_OK) break;
        } else if (c->reqtype == PROTO_REQ_MULTIBULK) {
            if (processMultibulkBuffer(c) != C_OK) break;
        } else {
            serverPanic("Unknown request type");
        }

        /* Multibulk processing could see a <= 0 length. */
        if (c->argc == 0) {
            resetClient(c);
        } else {
            /* Only reset the client when the command was executed. */
            if (processCommand(c) == C_OK)
                resetClient(c);
            /* 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) break;
        }
    }
    server.current_client = NULL;
}

通过processMultibulkBuffer()把请求的RESP协议格式的内容格式化,提取出来命令和对应的参数放到clients结构体的argc 和 argv 字段。最后就可以用processCommand()执行命令了

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. */
    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. */
    c->cmd = c->lastcmd = lookupCommand(c->argv[0]->ptr);
    if (!c->cmd) {
        flagTransaction(c);
        addReplyErrorFormat(c,"unknown command '%s'",
            (char*)c->argv[0]->ptr);
        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 */
    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. */
    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. */
    if (server.maxmemory) {
        int retval = freeMemoryIfNeeded();
        /* 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) && retval == C_ERR) {
            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. */
    if (((server.stop_writes_on_bgsave_err &&
          server.saveparamslen > 0 &&
          server.lastbgsave_status == C_ERR) ||
          server.aof_last_write_status == C_ERR) &&
        server.masterhost == NULL &&
        (c->cmd->flags & CMD_WRITE ||
         c->cmd->proc == pingCommand))
    {
        flagTransaction(c);
        if (server.aof_last_write_status == C_OK)
            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;
    }

    /* Don't accept write commands if this is a read only slave. But
     * accept write commands if this is our master. */
    if (server.masterhost && server.repl_slave_ro &&
        !(c->flags & CLIENT_MASTER) &&
        c->cmd->flags & CMD_WRITE)
    {
        addReply(c, shared.roslaveerr);
        return C_OK;
    }

    /* Only allow SUBSCRIBE and UNSUBSCRIBE in the context of Pub/Sub */
    if (c->flags & CLIENT_PUBSUB &&
        c->cmd->proc != pingCommand &&
        c->cmd->proc != subscribeCommand &&
        c->cmd->proc != unsubscribeCommand &&
        c->cmd->proc != psubscribeCommand &&
        c->cmd->proc != punsubscribeCommand) {
        addReplyError(c,"only (P)SUBSCRIBE / (P)UNSUBSCRIBE / PING / QUIT allowed in this context");
        return C_OK;
    }

    /* Only allow INFO and SLAVEOF when slave-serve-stale-data is no and
     * we are a slave with a broken link with master. */
    if (server.masterhost && server.repl_state != REPL_STATE_CONNECTED &&
        server.repl_serve_stale_data == 0 &&
        !(c->cmd->flags & CMD_STALE))
    {
        flagTransaction(c);
        addReply(c, shared.masterdownerr);
        return C_OK;
    }

    /* Loading DB? Return an error if the command has not the
     * CMD_LOADING flag. */
    if (server.loading && !(c->cmd->flags & CMD_LOADING)) {
        addReply(c, shared.loadingerr);
        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 {
        call(c,CMD_CALL_FULL);
        c->woff = server.master_repl_offset;
        if (listLength(server.ready_keys))
            handleClientsBlockedOnLists();
    }
    return C_OK;
}

执行完命令后redis会把对应请求的回复结果放到clients 结构体的buf 缓存中,等待之后处理
5. 在处理完请求之后(一般是执行相应的命令),将需要返回给client的内容放在redisClient结构中的buf成员中,然后将它对应的fd以可写事件加入poll中,对应的callback为sendReplyToClient。
6. 下一次aeApiPoll时,可写事件就绪,就会调用sendReplyToClient发回给客户 所以命令的接收跟命令的执行(queue也算是执行)是按顺序执行的,给client的回复是异步做的 所以对于同一个client,尽可能多地收集回复再一次性发出去能减少网络I/O的次数

命令交互的主要入口函数是readQueryFromClient,它从套接字中读取内容、再处理成argc/argv的格式、最后去执行:

处理完文件事件后就可以去处理时间事件了。

/* Process time events */
static int processTimeEvents(aeEventLoop *eventLoop) {
    int processed = 0;
    aeTimeEvent *te, *prev;
    long long maxId;
    time_t now = time(NULL);

    /* If the system clock is moved to the future, and then set back to the
     * right value, time events may be delayed in a random way. Often this
     * means that scheduled operations will not be performed soon enough.
     *
     * Here we try to detect system clock skews, and force all the time
     * events to be processed ASAP when this happens: the idea is that
     * processing events earlier is less dangerous than delaying them
     * indefinitely, and practice suggests it is. */
    if (now < eventLoop->lastTime) {
        te = eventLoop->timeEventHead;
        while(te) {
            te->when_sec = 0;
            te = te->next;
        }
    }
    eventLoop->lastTime = now;

    prev = NULL;
    te = eventLoop->timeEventHead;
    maxId = eventLoop->timeEventNextId-1;
    while(te) {
        long now_sec, now_ms;
        long long id;

        /* Remove events scheduled for deletion. */
        if (te->id == AE_DELETED_EVENT_ID) {
            aeTimeEvent *next = te->next;
            if (prev == NULL)
                eventLoop->timeEventHead = te->next;
            else
                prev->next = te->next;
            if (te->finalizerProc)
                te->finalizerProc(eventLoop, te->clientData);
            zfree(te);
            te = next;
            continue;
        }

        /* Make sure we don't process time events created by time events in
         * this iteration. Note that this check is currently useless: we always
         * add new timers on the head, however if we change the implementation
         * detail, this check may be useful again: we keep it here for future
         * defense. */
        if (te->id > maxId) {
            te = te->next;
            continue;
        }
        aeGetTime(&now_sec, &now_ms);
        if (now_sec > te->when_sec ||
            (now_sec == te->when_sec && now_ms >= te->when_ms))
        {
            int retval;

            id = te->id;
            retval = te->timeProc(eventLoop, id, te->clientData);
            processed++;
            if (retval != AE_NOMORE) {
                aeAddMillisecondsToNow(retval,&te->when_sec,&te->when_ms);
            } else {
                te->id = AE_DELETED_EVENT_ID;
            }
        }
        prev = te;
        te = te->next;
    }
    return processed;
}

调用时间事件回调函数serverCron 来执行时间事件

int serverCron(struct aeEventLoop *eventLoop, long long id, void *clientData) {
    int j;
    UNUSED(eventLoop);
    UNUSED(id);
    UNUSED(clientData);

    /* Software watchdog: deliver the SIGALRM that will reach the signal
     * handler if we don't return here fast enough. */
    if (server.watchdog_period) watchdogScheduleSignal(server.watchdog_period);

    /* Update the time cache. */
    updateCachedTime();

    run_with_period(100) {
        trackInstantaneousMetric(STATS_METRIC_COMMAND,server.stat_numcommands);
        trackInstantaneousMetric(STATS_METRIC_NET_INPUT,
                server.stat_net_input_bytes);
        trackInstantaneousMetric(STATS_METRIC_NET_OUTPUT,
                server.stat_net_output_bytes);
    }

    /* We have just LRU_BITS bits per object for LRU information.
     * So we use an (eventually wrapping) LRU clock.
     *
     * Note that even if the counter wraps it's not a big problem,
     * everything will still work but some object will appear younger
     * to Redis. However for this to happen a given object should never be
     * touched for all the time needed to the counter to wrap, which is
     * not likely.
     *
     * Note that you can change the resolution altering the
     * LRU_CLOCK_RESOLUTION define. */
    server.lruclock = getLRUClock();

    /* Record the max memory used since the server was started. */
    if (zmalloc_used_memory() > server.stat_peak_memory)
        server.stat_peak_memory = zmalloc_used_memory();

    /* Sample the RSS here since this is a relatively slow call. */
    server.resident_set_size = zmalloc_get_rss();

    /* We received a SIGTERM, shutting down here in a safe way, as it is
     * not ok doing so inside the signal handler. */
    if (server.shutdown_asap) {
        if (prepareForShutdown(SHUTDOWN_NOFLAGS) == C_OK) exit(0);
        serverLog(LL_WARNING,"SIGTERM received but errors trying to shut down the server, check the logs for more information");
        server.shutdown_asap = 0;
    }

    /* Show some info about non-empty databases */
    run_with_period(5000) {
        for (j = 0; j < server.dbnum; j++) {
            long long size, used, vkeys;

            size = dictSlots(server.db[j].dict);
            used = dictSize(server.db[j].dict);
            vkeys = dictSize(server.db[j].expires);
            if (used || vkeys) {
                serverLog(LL_VERBOSE,"DB %d: %lld keys (%lld volatile) in %lld slots HT.",j,used,vkeys,size);
                /* dictPrintStats(server.dict); */
            }
        }
    }

    /* Show information about connected clients */
    if (!server.sentinel_mode) {
        run_with_period(5000) {
            serverLog(LL_VERBOSE,
                "%lu clients connected (%lu slaves), %zu bytes in use",
                listLength(server.clients)-listLength(server.slaves),
                listLength(server.slaves),
                zmalloc_used_memory());
        }
    }

    /* We need to do a few operations on clients asynchronously. */
    clientsCron();

    /* Handle background operations on Redis databases. */
    databasesCron();

    /* Start a scheduled AOF rewrite if this was requested by the user while
     * a BGSAVE was in progress. */
    if (server.rdb_child_pid == -1 && server.aof_child_pid == -1 &&
        server.aof_rewrite_scheduled)
    {
        rewriteAppendOnlyFileBackground();
    }

    /* Check if a background saving or AOF rewrite in progress terminated. */
    if (server.rdb_child_pid != -1 || server.aof_child_pid != -1 ||
        ldbPendingChildren())
    {
        int statloc;
        pid_t pid;

        if ((pid = wait3(&statloc,WNOHANG,NULL)) != 0) {
            int exitcode = WEXITSTATUS(statloc);
            int bysignal = 0;

            if (WIFSIGNALED(statloc)) bysignal = WTERMSIG(statloc);

            if (pid == -1) {
                serverLog(LL_WARNING,"wait3() returned an error: %s. "
                    "rdb_child_pid = %d, aof_child_pid = %d",
                    strerror(errno),
                    (int) server.rdb_child_pid,
                    (int) server.aof_child_pid);
            } else if (pid == server.rdb_child_pid) {
                backgroundSaveDoneHandler(exitcode,bysignal);
            } else if (pid == server.aof_child_pid) {
                backgroundRewriteDoneHandler(exitcode,bysignal);
            } else {
                if (!ldbRemoveChild(pid)) {
                    serverLog(LL_WARNING,
                        "Warning, detected child with unmatched pid: %ld",
                        (long)pid);
                }
            }
            updateDictResizePolicy();
        }
    } else {
        /* If there is not a background saving/rewrite in progress check if
         * we have to save/rewrite now */
         for (j = 0; j < server.saveparamslen; j++) {
            struct saveparam *sp = server.saveparams+j;

            /* Save if we reached the given amount of changes,
             * the given amount of seconds, and if the latest bgsave was
             * successful or if, in case of an error, at least
             * CONFIG_BGSAVE_RETRY_DELAY seconds already elapsed. */
            if (server.dirty >= sp->changes &&
                server.unixtime-server.lastsave > sp->seconds &&
                (server.unixtime-server.lastbgsave_try >
                 CONFIG_BGSAVE_RETRY_DELAY ||
                 server.lastbgsave_status == C_OK))
            {
                serverLog(LL_NOTICE,"%d changes in %d seconds. Saving...",
                    sp->changes, (int)sp->seconds);
                rdbSaveBackground(server.rdb_filename);
                break;
            }
         }

         /* Trigger an AOF rewrite if needed */
         if (server.rdb_child_pid == -1 &&
             server.aof_child_pid == -1 &&
             server.aof_rewrite_perc &&
             server.aof_current_size > server.aof_rewrite_min_size)
         {
            long long base = server.aof_rewrite_base_size ?
                            server.aof_rewrite_base_size : 1;
            long long growth = (server.aof_current_size*100/base) - 100;
            if (growth >= server.aof_rewrite_perc) {
                serverLog(LL_NOTICE,"Starting automatic rewriting of AOF on %lld%% growth",growth);
                rewriteAppendOnlyFileBackground();
            }
         }
    }


    /* AOF postponed flush: Try at every cron cycle if the slow fsync
     * completed. */
    if (server.aof_flush_postponed_start) flushAppendOnlyFile(0);

    /* AOF write errors: in this case we have a buffer to flush as well and
     * clear the AOF error in case of success to make the DB writable again,
     * however to try every second is enough in case of 'hz' is set to
     * an higher frequency. */
    run_with_period(1000) {
        if (server.aof_last_write_status == C_ERR)
            flushAppendOnlyFile(0);
    }

    /* Close clients that need to be closed asynchronous */
    freeClientsInAsyncFreeQueue();

    /* Clear the paused clients flag if needed. */
    clientsArePaused(); /* Don't check return value, just use the side effect. */

    /* Replication cron function -- used to reconnect to master,
     * detect transfer failures, start background RDB transfers and so forth. */
    run_with_period(1000) replicationCron();

    /* Run the Redis Cluster cron. */
    run_with_period(100) {
        if (server.cluster_enabled) clusterCron();
    }

    /* Run the Sentinel timer if we are in sentinel mode. */
    run_with_period(100) {
        if (server.sentinel_mode) sentinelTimer();
    }

    /* Cleanup expired MIGRATE cached sockets. */
    run_with_period(1000) {
        migrateCloseTimedoutSockets();
    }

    /* Start a scheduled BGSAVE if the corresponding flag is set. This is
     * useful when we are forced to postpone a BGSAVE because an AOF
     * rewrite is in progress.
     *
     * Note: this code must be after the replicationCron() call above so
     * make sure when refactoring this file to keep this order. This is useful
     * because we want to give priority to RDB savings for replication. */
    if (server.rdb_child_pid == -1 && server.aof_child_pid == -1 &&
        server.rdb_bgsave_scheduled &&
        (server.unixtime-server.lastbgsave_try > CONFIG_BGSAVE_RETRY_DELAY ||
         server.lastbgsave_status == C_OK))
    {
        if (rdbSaveBackground(server.rdb_filename) == C_OK)
            server.rdb_bgsave_scheduled = 0;
    }

    server.cronloops++;
    return 1000/server.hz;
}

里面会调用clientsCron() 处理链接超时的客户端,处理需要对查询缓存重新分配大小的客户端。

然后另一个就是databaseCron(),里面activeExpireCycle()负责处理过期键,从存放过期键的DB中随机采样key,进行删除,如果某次删除的key比例超过了采样数量的25%,就会再采样删除一次。 还有一个功能就是做rehash操作。

void activeExpireCycle(int type) {
    /* This function has some global state in order to continue the work
     * incrementally across calls. */
    static unsigned int current_db = 0; /* Last DB tested. */
    static int timelimit_exit = 0;      /* Time limit hit in previous call? */
    static long long last_fast_cycle = 0; /* When last fast cycle ran. */

    int j, iteration = 0;
    int dbs_per_call = CRON_DBS_PER_CALL;
    long long start = ustime(), timelimit;

    if (type == ACTIVE_EXPIRE_CYCLE_FAST) {
        /* Don't start a fast cycle if the previous cycle did not exited
         * for time limt. Also don't repeat a fast cycle for the same period
         * as the fast cycle total duration itself. */
        if (!timelimit_exit) return;
        if (start < last_fast_cycle + ACTIVE_EXPIRE_CYCLE_FAST_DURATION*2) return;
        last_fast_cycle = start;
    }

    /* We usually should test CRON_DBS_PER_CALL per iteration, with
     * two exceptions:
     *
     * 1) Don't test more DBs than we have.
     * 2) If last time we hit the time limit, we want to scan all DBs
     * in this iteration, as there is work to do in some DB and we don't want
     * expired keys to use memory for too much time. */
    if (dbs_per_call > server.dbnum || timelimit_exit)
        dbs_per_call = server.dbnum;

    /* We can use at max ACTIVE_EXPIRE_CYCLE_SLOW_TIME_PERC percentage of CPU time
     * per iteration. Since this function gets called with a frequency of
     * server.hz times per second, the following is the max amount of
     * microseconds we can spend in this function. */
    timelimit = 1000000*ACTIVE_EXPIRE_CYCLE_SLOW_TIME_PERC/server.hz/100;
    timelimit_exit = 0;
    if (timelimit <= 0) timelimit = 1;

    if (type == ACTIVE_EXPIRE_CYCLE_FAST)
        timelimit = ACTIVE_EXPIRE_CYCLE_FAST_DURATION; /* in microseconds. */

    for (j = 0; j < dbs_per_call; j++) {
        int expired;
        redisDb *db = server.db+(current_db % server.dbnum);

        /* Increment the DB now so we are sure if we run out of time
         * in the current DB we'll restart from the next. This allows to
         * distribute the time evenly across DBs. */
        current_db++;

        /* Continue to expire if at the end of the cycle more than 25%
         * of the keys were expired. */
        do {
            unsigned long num, slots;
            long long now, ttl_sum;
            int ttl_samples;

            /* If there is nothing to expire try next DB ASAP. */
            if ((num = dictSize(db->expires)) == 0) {
                db->avg_ttl = 0;
                break;
            }
            slots = dictSlots(db->expires);
            now = mstime();

            /* When there are less than 1% filled slots getting random
             * keys is expensive, so stop here waiting for better times...
             * The dictionary will be resized asap. */
            if (num && slots > DICT_HT_INITIAL_SIZE &&
                (num*100/slots < 1)) break;

            /* The main collection cycle. Sample random keys among keys
             * with an expire set, checking for expired ones. */
            expired = 0;
            ttl_sum = 0;
            ttl_samples = 0;

            if (num > ACTIVE_EXPIRE_CYCLE_LOOKUPS_PER_LOOP)
                num = ACTIVE_EXPIRE_CYCLE_LOOKUPS_PER_LOOP;

            while (num--) {
                dictEntry *de;
                long long ttl;

                if ((de = dictGetRandomKey(db->expires)) == NULL) break;
                ttl = dictGetSignedIntegerVal(de)-now;
                if (activeExpireCycleTryExpire(db,de,now)) expired++;
                if (ttl > 0) {
                    /* We want the average TTL of keys yet not expired. */
                    ttl_sum += ttl;
                    ttl_samples++;
                }
            }

            /* Update the average TTL stats for this database. */
            if (ttl_samples) {
                long long avg_ttl = ttl_sum/ttl_samples;

                /* Do a simple running average with a few samples.
                 * We just use the current estimate with a weight of 2%
                 * and the previous estimate with a weight of 98%. */
                if (db->avg_ttl == 0) db->avg_ttl = avg_ttl;
                db->avg_ttl = (db->avg_ttl/50)*49 + (avg_ttl/50);
            }

            /* We can't block forever here even if there are many keys to
             * expire. So after a given amount of milliseconds return to the
             * caller waiting for the other active expire cycle. */
            iteration++;
            if ((iteration & 0xf) == 0) { /* check once every 16 iterations. */
                long long elapsed = ustime()-start;

                latencyAddSampleIfNeeded("expire-cycle",elapsed/1000);
                if (elapsed > timelimit) timelimit_exit = 1;
            }
            if (timelimit_exit) return;
            /* We don't repeat the cycle if there are less than 25% of keys
             * found expired in the current DB. */
        } while (expired > ACTIVE_EXPIRE_CYCLE_LOOKUPS_PER_LOOP/4);
    }
}

文章1