redis源码分析之networking.c

#include "server.h"
#include "atomicvar.h"
#include <sys/uio.h>
#include <math.h>
#include <ctype.h>

static void setProtocolError(const char *errstr, client *c, int pos);

/* Return the size consumed from the allocator, for the specified SDS string,
 * including internal fragmentation. This function is used in order to compute
 * the client output buffer size. */
size_t sdsZmallocSize(sds s) {
    void *sh = sdsAllocPtr(s);
    return zmalloc_size(sh);
}

/* Return the amount of memory used by the sds string at object->ptr
 * for a string object. */
size_t getStringObjectSdsUsedMemory(robj *o) {
    serverAssertWithInfo(NULL,o,o->type == OBJ_STRING);
    switch(o->encoding) {
    case OBJ_ENCODING_RAW: return sdsZmallocSize(o->ptr);
    case OBJ_ENCODING_EMBSTR: return zmalloc_size(o)-sizeof(robj);
    default: return 0; /* Just integer encoding for now. */
    }
}

/* Client.reply list dup and free methods. */
void *dupClientReplyValue(void *o) {
    return sdsdup(o);
}

void freeClientReplyValue(void *o) {
    sdsfree(o);
}

int listMatchObjects(void *a, void *b) {
    return equalStringObjects(a,b);
}

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);
    uint64_t client_id;
    atomicGetIncr(server.next_client_id,client_id,1);
    c->id = client_id;
    c->fd = fd;
    c->name = NULL;
    c->bufpos = 0;
    c->querybuf = sdsempty();
    c->pending_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->read_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,freeClientReplyValue);
    listSetDupMethod(c->reply,dupClientReplyValue);
    c->btype = BLOCKED_NONE;
    c->bpop.timeout = 0;
    c->bpop.keys = dictCreate(&objectKeyPointerValueDictType,NULL);
    c->bpop.target = NULL;
    c->bpop.numreplicas = 0;
    c->bpop.reploffset = 0;
    c->woff = 0;
    c->watched_keys = listCreate();
    c->pubsub_channels = dictCreate(&objectKeyPointerValueDictType,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;
}

/* This function is called every time we are going to transmit new data
 * to the client. The behavior is the following:
 *
 * If the client should receive new data (normal clients will) the function
 * returns C_OK, and make sure to install the write handler in our event
 * loop so that when the socket is writable new data gets written.
 *
 * If the client should not receive new data, because it is a fake client
 * (used to load AOF in memory), a master or because the setup of the write
 * handler failed, the function returns C_ERR.
 *
 * The function may return C_OK without actually installing the write
 * event handler in the following cases:
 *
 * 1) The event handler should already be installed since the output buffer
 *    already contains something.
 * 2) The client is a slave but not yet online, so we want to just accumulate
 *    writes in the buffer but not actually sending them yet.
 *
 * Typically gets called every time a reply is built, before adding more
 * data to the clients output buffers. If the function returns C_ERR no
 * data should be appended to the output buffers. */
int prepareClientToWrite(client *c) {
    /* If it's the Lua client we always return ok without installing any
     * handler since there is no socket at all. */
    if (c->flags & (CLIENT_LUA|CLIENT_MODULE)) return C_OK;

    /* CLIENT REPLY OFF / SKIP handling: don't send replies. */
    if (c->flags & (CLIENT_REPLY_OFF|CLIENT_REPLY_SKIP)) return C_ERR;

    /* Masters don't receive replies, unless CLIENT_MASTER_FORCE_REPLY flag
     * is set. */
    if ((c->flags & CLIENT_MASTER) &&
        !(c->flags & CLIENT_MASTER_FORCE_REPLY)) return C_ERR;

    if (c->fd <= 0) return C_ERR; /* Fake client for AOF loading. */

    /* Schedule the client to write the output buffers to the socket only
     * if not already done (there were no pending writes already and the client
     * was yet not flagged), and, for slaves, if the slave can actually
     * receive writes at this stage. */
    if (!clientHasPendingReplies(c) &&
        !(c->flags & CLIENT_PENDING_WRITE) &&
        (c->replstate == REPL_STATE_NONE ||
         (c->replstate == SLAVE_STATE_ONLINE && !c->repl_put_online_on_ack)))
    {
        /* Here instead of installing the write handler, we just flag the
         * client and put it into a list of clients that have something
         * to write to the socket. This way before re-entering the event
         * loop, we can try to directly write to the client sockets avoiding
         * a system call. We'll only really install the write handler if
         * we'll not be able to write the whole reply at once. */
        c->flags |= CLIENT_PENDING_WRITE;
        listAddNodeHead(server.clients_pending_write,c);
    }

    /* Authorize the caller to queue in the output buffer of this client. */
    return C_OK;
}

/* -----------------------------------------------------------------------------
 * Low level functions to add more data to output buffers.
 * -------------------------------------------------------------------------- */

int _addReplyToBuffer(client *c, const char *s, size_t len) {
    size_t available = sizeof(c->buf)-c->bufpos;

    if (c->flags & CLIENT_CLOSE_AFTER_REPLY) return C_OK;

    /* If there already are entries in the reply list, we cannot
     * add anything more to the static buffer. */
    if (listLength(c->reply) > 0) return C_ERR;

    /* Check that the buffer has enough space available for this string. */
    if (len > available) return C_ERR;

    memcpy(c->buf+c->bufpos,s,len);
    c->bufpos+=len;
    return C_OK;
}

void _addReplyObjectToList(client *c, robj *o) {
    if (c->flags & CLIENT_CLOSE_AFTER_REPLY) return;

    if (listLength(c->reply) == 0) {
        sds s = sdsdup(o->ptr);
        listAddNodeTail(c->reply,s);
        c->reply_bytes += sdslen(s);
    } else {
        listNode *ln = listLast(c->reply);
        sds tail = listNodeValue(ln);

        /* Append to this object when possible. If tail == NULL it was
         * set via addDeferredMultiBulkLength(). */
        if (tail && sdslen(tail)+sdslen(o->ptr) <= PROTO_REPLY_CHUNK_BYTES) {
            tail = sdscatsds(tail,o->ptr);
            listNodeValue(ln) = tail;
            c->reply_bytes += sdslen(o->ptr);
        } else {
            sds s = sdsdup(o->ptr);
            listAddNodeTail(c->reply,s);
            c->reply_bytes += sdslen(s);
        }
    }
    asyncCloseClientOnOutputBufferLimitReached(c);
}

/* This method takes responsibility over the sds. When it is no longer
 * needed it will be free'd, otherwise it ends up in a robj. */
void _addReplySdsToList(client *c, sds s) {
    if (c->flags & CLIENT_CLOSE_AFTER_REPLY) {
        sdsfree(s);
        return;
    }

    if (listLength(c->reply) == 0) {
        listAddNodeTail(c->reply,s);
        c->reply_bytes += sdslen(s);
    } else {
        listNode *ln = listLast(c->reply);
        sds tail = listNodeValue(ln);

        /* Append to this object when possible. If tail == NULL it was
         * set via addDeferredMultiBulkLength(). */
        if (tail && sdslen(tail)+sdslen(s) <= PROTO_REPLY_CHUNK_BYTES) {
            tail = sdscatsds(tail,s);
            listNodeValue(ln) = tail;
            c->reply_bytes += sdslen(s);
            sdsfree(s);
        } else {
            listAddNodeTail(c->reply,s);
            c->reply_bytes += sdslen(s);
        }
    }
    asyncCloseClientOnOutputBufferLimitReached(c);
}

void _addReplyStringToList(client *c, const char *s, size_t len) {
    if (c->flags & CLIENT_CLOSE_AFTER_REPLY) return;

    if (listLength(c->reply) == 0) {
        sds node = sdsnewlen(s,len);
        listAddNodeTail(c->reply,node);
        c->reply_bytes += len;
    } else {
        listNode *ln = listLast(c->reply);
        sds tail = listNodeValue(ln);

        /* Append to this object when possible. If tail == NULL it was
         * set via addDeferredMultiBulkLength(). */
        if (tail && sdslen(tail)+len <= PROTO_REPLY_CHUNK_BYTES) {
            tail = sdscatlen(tail,s,len);
            listNodeValue(ln) = tail;
            c->reply_bytes += len;
        } else {
            sds node = sdsnewlen(s,len);
            listAddNodeTail(c->reply,node);
            c->reply_bytes += len;
        }
    }
    asyncCloseClientOnOutputBufferLimitReached(c);
}

/* -----------------------------------------------------------------------------
 * Higher level functions to queue data on the client output buffer.
 * The following functions are the ones that commands implementations will call.
 * -------------------------------------------------------------------------- */

void addReply(client *c, robj *obj) {
    if (prepareClientToWrite(c) != C_OK) return;

    /* This is an important place where we can avoid copy-on-write
     * when there is a saving child running, avoiding touching the
     * refcount field of the object if it's not needed.
     *
     * If the encoding is RAW and there is room in the static buffer
     * we'll be able to send the object to the client without
     * messing with its page. */
    if (sdsEncodedObject(obj)) {
        if (_addReplyToBuffer(c,obj->ptr,sdslen(obj->ptr)) != C_OK)
            _addReplyObjectToList(c,obj);
    } else if (obj->encoding == OBJ_ENCODING_INT) {
        /* Optimization: if there is room in the static buffer for 32 bytes
         * (more than the max chars a 64 bit integer can take as string) we
         * avoid decoding the object and go for the lower level approach. */
        if (listLength(c->reply) == 0 && (sizeof(c->buf) - c->bufpos) >= 32) {
            char buf[32];
            int len;

            len = ll2string(buf,sizeof(buf),(long)obj->ptr);
            if (_addReplyToBuffer(c,buf,len) == C_OK)
                return;
            /* else... continue with the normal code path, but should never
             * happen actually since we verified there is room. */
        }
        obj = getDecodedObject(obj);
        if (_addReplyToBuffer(c,obj->ptr,sdslen(obj->ptr)) != C_OK)
            _addReplyObjectToList(c,obj);
        decrRefCount(obj);
    } else {
        serverPanic("Wrong obj->encoding in addReply()");
    }
}

void addReplySds(client *c, sds s) {
    if (prepareClientToWrite(c) != C_OK) {
        /* The caller expects the sds to be free'd. */
        sdsfree(s);
        return;
    }
    if (_addReplyToBuffer(c,s,sdslen(s)) == C_OK) {
        sdsfree(s);
    } else {
        /* This method free's the sds when it is no longer needed. */
        _addReplySdsToList(c,s);
    }
}

/* This low level function just adds whatever protocol you send it to the
 * client buffer, trying the static buffer initially, and using the string
 * of objects if not possible.
 *
 * It is efficient because does not create an SDS object nor an Redis object
 * if not needed. The object will only be created by calling
 * _addReplyStringToList() if we fail to extend the existing tail object
 * in the list of objects. */
void addReplyString(client *c, const char *s, size_t len) {
    if (prepareClientToWrite(c) != C_OK) return;
    if (_addReplyToBuffer(c,s,len) != C_OK)
        _addReplyStringToList(c,s,len);
}

void addReplyErrorLength(client *c, const char *s, size_t len) {
    addReplyString(c,"-ERR ",5);
    addReplyString(c,s,len);
    addReplyString(c,"\r\n",2);
}

void addReplyError(client *c, const char *err) {
    addReplyErrorLength(c,err,strlen(err));
}

void addReplyErrorFormat(client *c, const char *fmt, ...) {
    size_t l, j;
    va_list ap;
    va_start(ap,fmt);
    sds s = sdscatvprintf(sdsempty(),fmt,ap);
    va_end(ap);
    /* Make sure there are no newlines in the string, otherwise invalid protocol
     * is emitted. */
    l = sdslen(s);
    for (j = 0; j < l; j++) {
        if (s[j] == '\r' || s[j] == '\n') s[j] = ' ';
    }
    addReplyErrorLength(c,s,sdslen(s));
    sdsfree(s);
}

void addReplyStatusLength(client *c, const char *s, size_t len) {
    addReplyString(c,"+",1);
    addReplyString(c,s,len);
    addReplyString(c,"\r\n",2);
}

void addReplyStatus(client *c, const char *status) {
    addReplyStatusLength(c,status,strlen(status));
}

void addReplyStatusFormat(client *c, const char *fmt, ...) {
    va_list ap;
    va_start(ap,fmt);
    sds s = sdscatvprintf(sdsempty(),fmt,ap);
    va_end(ap);
    addReplyStatusLength(c,s,sdslen(s));
    sdsfree(s);
}

/* Adds an empty object to the reply list that will contain the multi bulk
 * length, which is not known when this function is called. */
void *addDeferredMultiBulkLength(client *c) {
    /* Note that we install the write event here even if the object is not
     * ready to be sent, since we are sure that before returning to the
     * event loop setDeferredMultiBulkLength() will be called. */
    if (prepareClientToWrite(c) != C_OK) return NULL;
    listAddNodeTail(c->reply,NULL); /* NULL is our placeholder. */
    return listLast(c->reply);
}

/* Populate the length object and try gluing it to the next chunk. */
void setDeferredMultiBulkLength(client *c, void *node, long length) {
    listNode *ln = (listNode*)node;
    sds len, next;

    /* Abort when *node is NULL: when the client should not accept writes
     * we return NULL in addDeferredMultiBulkLength() */
    if (node == NULL) return;

    len = sdscatprintf(sdsnewlen("*",1),"%ld\r\n",length);
    listNodeValue(ln) = len;
    c->reply_bytes += sdslen(len);
    if (ln->next != NULL) {
        next = listNodeValue(ln->next);

        /* Only glue when the next node is non-NULL (an sds in this case) */
        if (next != N