服務器
Redis 服務器是典型的一對多服務器程序：一個服務器可以與多個客戶端建立網絡連接，每個客戶端可以向服務器發送命令請求,而服務器接收並處理客戶端發送的命令請求，並向客戶端命令回覆。
- 那麼問題來了，每個服務端可以維護多少個客戶端連接？
- 服務器是如何維護客戶端連接的？
- 每個客戶端可以發送多大命令？
- 客戶端可以存放的value最大有多大？
服務器初始化
redis.c/main函數
初始化服務器狀態結構
載入配置項
void initServerConfig(void) {
int j;
updateCachedTime(1);
getRandomHexChars(server.runid,CONFIG_RUN_ID_SIZE);
server.runid[CONFIG_RUN_ID_SIZE] = '\0';
changeReplicationId();
clearReplicationId2();
server.timezone = getTimeZone(); /* Initialized by tzset(). */
server.configfile = NULL;
server.executable = NULL;
server.arch_bits = (sizeof(long) == 8) ? 64 : 32;
server.bindaddr_count = 0;
server.unixsocketperm = CONFIG_DEFAULT_UNIX_SOCKET_PERM;
server.ipfd_count = 0;
server.tlsfd_count = 0;
server.sofd = -1;
server.active_expire_enabled = 1;
server.client_max_querybuf_len = PROTO_MAX_QUERYBUF_LEN;
server.saveparams = NULL;
server.loading = 0;
server.logfile = zstrdup(CONFIG_DEFAULT_LOGFILE);
server.aof_state = AOF_OFF;
server.aof_rewrite_base_size = 0;
server.aof_rewrite_scheduled = 0;
server.aof_flush_sleep = 0;
server.aof_last_fsync = time(NULL);
server.aof_rewrite_time_last = -1;
server.aof_rewrite_time_start = -1;
server.aof_lastbgrewrite_status = C_OK;
server.aof_delayed_fsync = 0;
server.aof_fd = -1;
server.aof_selected_db = -1; /* Make sure the first time will not match */
server.aof_flush_postponed_start = 0;
// 省略...
}
初始化服務器
- 爲服務器設置進程信號處理器
signal(SIGHUP, SIG_IGN);
signal(SIGPIPE, SIG_IGN);
setupSignalHandlers();
- 創建 clients/slaves/等
/* Initialization after setting defaults from the config system. */
server.aof_state = server.aof_enabled ? AOF_ON : AOF_OFF;
server.hz = server.config_hz;
server.pid = getpid();
server.current_client = NULL;
server.fixed_time_expire = 0;
server.clients = listCreate();
server.clients_index = raxNew();
server.clients_to_close = listCreate();
server.slaves = listCreate();
server.monitors = listCreate();
server.clients_pending_write = listCreate();
server.clients_pending_read = 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();
- 創建共享對象
createSharedObjects();
- 打開服務器的監聽端口
/* Open the TCP listening socket for the user commands. */
if (server.port != 0 &&
listenToPort(server.port,server.ipfd,&server.ipfd_count) == C_ERR)
exit(1);
if (server.tls_port != 0 &&
listenToPort(server.tls_port,server.tlsfd,&server.tlsfd_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.tlsfd_count == 0 && server.sofd < 0) {
serverLog(LL_WARNING, "Configured to not listen anywhere, exiting.");
exit(1);
}
- 創建數據庫
/* 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].expires_cursor = 0;
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();
listSetFreeMethod(server.db[j].defrag_later,(void (*)(void*))sdsfree);
}
evictionPoolAlloc(); /* Initialize the LRU keys pool. */
- 爲serverCron函數創建時間事件
/* 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);
}
- 創建一個事件處理程序以接受TCP和Unix域套接字中的新連接。
/* Create an event handler for accepting new connections in TCP and Unix
* domain sockets. */
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.");
}
}
for (j = 0; j < server.tlsfd_count; j++) {
if (aeCreateFileEvent(server.el, server.tlsfd[j], AE_READABLE,
acceptTLSHandler,NULL) == AE_ERR)
{
serverPanic(
"Unrecoverable error creating server.tlsfd 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.");
- 如果AOF持久化功能已經打開， 那麼打開AOF文件，如果文件不存在，那麼就創建一個新的AOF文件，爲AOF寫入做好準備。
/* 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);
}
}
- 創建保存發佈/訂閱功能的結構
server.pubsub_channels = dictCreate(&keylistDictType,NULL);
server.pubsub_patterns = listCreate();
listSetFreeMethod(server.pubsub_patterns,freePubsubPattern);
listSetMatchMethod(server.pubsub_patterns,listMatchPubsubPattern);
10 .others
replicationScriptCacheInit();
scriptingInit(1);
slowlogInit();
latencyMonitorInit();
事後檢查
redisSetProcTitle(argv[0]);
redisAsciiArt();
checkTcpBacklogSettings();
加載持久化數據
如果不是新的redis服務器，需要加載持久化的數據
loadDataFromDisk();
/* Function called at startup to load RDB or AOF file in memory. */
void loadDataFromDisk(void) {
long long start = ustime();
if (server.aof_state == AOF_ON) {
if (loadAppendOnlyFile(server.aof_filename) == C_OK)
serverLog(LL_NOTICE,"DB loaded from append only file: %.3f seconds",(float)(ustime()-start)/1000000);
} else {
rdbSaveInfo rsi = RDB_SAVE_INFO_INIT;
if (rdbLoad(server.rdb_filename,&rsi,RDBFLAGS_NONE) == C_OK) {
serverLog(LL_NOTICE,"DB loaded from disk: %.3f seconds",
(float)(ustime()-start)/1000000);
/* Restore the replication ID / offset from the RDB file. */
if ((server.masterhost ||
(server.cluster_enabled &&
nodeIsSlave(server.cluster->myself))) &&
rsi.repl_id_is_set &&
rsi.repl_offset != -1 &&
/* Note that older implementations may save a repl_stream_db
* of -1 inside the RDB file in a wrong way, see more
* information in function rdbPopulateSaveInfo. */
rsi.repl_stream_db != -1)
{
memcpy(server.replid,rsi.repl_id,sizeof(server.replid));
server.master_repl_offset = rsi.repl_offset;
/* If we are a slave, create a cached master from this
* information, in order to allow partial resynchronizations
* with masters. */
replicationCacheMasterUsingMyself();
selectDb(server.cached_master,rsi.repl_stream_db);
}
} else if (errno != ENOENT) {
serverLog(LL_WARNING,"Fatal error loading the DB: %s. Exiting.",strerror(errno));
exit(1);
}
}
}
優先使用AOF
執行事件循環
void aeMain(aeEventLoop *eventLoop) {
eventLoop->stop = 0;
while (!eventLoop->stop) {
if (eventLoop->beforesleep != NULL)
eventLoop->beforesleep(eventLoop);
aeProcessEvents(eventLoop, AE_ALL_EVENTS|AE_CALL_AFTER_SLEEP);
}
}
服務器處理客戶端請求
參考《Redis讀書筆記》事件設計
定時處理
參考《Redis讀書筆記》事件設計
數據結構
- RedisServer
struct redisServer {
/* General */
pid_t pid; /* Main process pid. */
char *configfile; /* Absolute config file path, or NULL */
char *executable; /* Absolute executable file path. */
char **exec_argv; /* Executable argv vector (copy). */
int dynamic_hz; /* Change hz value depending on # of clients. */
int config_hz; /* Configured HZ value. May be different than
the actual 'hz' field value if dynamic-hz
is enabled. */
int hz; /* serverCron() calls frequency in hertz */
redisDb *db;
dict *commands; /* Command table */
dict *orig_commands; /* Command table before command renaming. */
aeEventLoop *el;
_Atomic unsigned int lruclock; /* Clock for LRU eviction */
int shutdown_asap; /* SHUTDOWN needed ASAP */
int activerehashing; /* Incremental rehash in serverCron() */
int active_defrag_running; /* Active defragmentation running (holds current scan aggressiveness) */
char *pidfile; /* PID file path */
int arch_bits; /* 32 or 64 depending on sizeof(long) */
int cronloops; /* Number of times the cron function run */
char runid[CONFIG_RUN_ID_SIZE+1]; /* ID always different at every exec. */
int sentinel_mode; /* True if this instance is a Sentinel. */
size_t initial_memory_usage; /* Bytes used after initialization. */
int always_show_logo; /* Show logo even for non-stdout logging. */
/* Modules */
dict *moduleapi; /* Exported core APIs dictionary for modules. */
dict *sharedapi; /* Like moduleapi but containing the APIs that
modules share with each other. */
list *loadmodule_queue; /* List of modules to load at startup. */
int module_blocked_pipe[2]; /* Pipe used to awake the event loop if a
client blocked on a module command needs
to be processed. */
pid_t module_child_pid; /* PID of module child */
/* Networking */
int port; /* TCP listening port */
int tls_port; /* TLS listening port */
int tcp_backlog; /* TCP listen() backlog */
char *bindaddr[CONFIG_BINDADDR_MAX]; /* Addresses we should bind to */
int bindaddr_count; /* Number of addresses in server.bindaddr[] */
char *unixsocket; /* UNIX socket path */
mode_t unixsocketperm; /* UNIX socket permission */
int ipfd[CONFIG_BINDADDR_MAX]; /* TCP socket file descriptors */
int ipfd_count; /* Used slots in ipfd[] */
int tlsfd[CONFIG_BINDADDR_MAX]; /* TLS socket file descriptors */
int tlsfd_count; /* Used slots in tlsfd[] */
int sofd; /* Unix socket file descriptor */
int cfd[CONFIG_BINDADDR_MAX];/* Cluster bus listening socket */
int cfd_count; /* Used slots in cfd[] */
list *clients; /* List of active clients */
list *clients_to_close; /* Clients to close asynchronously */
list *clients_pending_write; /* There is to write or install handler. */
list *clients_pending_read; /* Client has pending read socket buffers. */
list *slaves, *monitors; /* List of slaves and MONITORs */
client *current_client; /* Current client executing the command. */
long fixed_time_expire; /* If > 0, expire keys against server.mstime. */
rax *clients_index; /* Active clients dictionary by client ID. */
int clients_paused; /* True if clients are currently paused */
mstime_t clients_pause_end_time; /* Time when we undo clients_paused */
char neterr[ANET_ERR_LEN]; /* Error buffer for anet.c */
dict *migrate_cached_sockets;/* MIGRATE cached sockets */
_Atomic uint64_t next_client_id; /* Next client unique ID. Incremental. */
int protected_mode; /* Don't accept external connections. */
int gopher_enabled; /* If true the server will reply to gopher
queries. Will still serve RESP2 queries. */
int io_threads_num; /* Number of IO threads to use. */
int io_threads_do_reads; /* Read and parse from IO threads? */
/* RDB / AOF loading information */
int loading; /* We are loading data from disk if true */
off_t loading_total_bytes;
off_t loading_loaded_bytes;
time_t loading_start_time;
off_t loading_process_events_interval_bytes;
/* Fast pointers to often looked up command */
struct redisCommand *delCommand, *multiCommand, *lpushCommand,
*lpopCommand, *rpopCommand, *zpopminCommand,
*zpopmaxCommand, *sremCommand, *execCommand,
*expireCommand, *pexpireCommand, *xclaimCommand,
*xgroupCommand;
/* Fields used only for stats */
time_t stat_starttime; /* Server start time */
long long stat_numcommands; /* Number of processed commands */
long long stat_numconnections; /* Number of connections received */
long long stat_expiredkeys; /* Number of expired keys */
double stat_expired_stale_perc; /* Percentage of keys probably expired */
long long stat_expired_time_cap_reached_count; /* Early expire cylce stops.*/
long long stat_expire_cycle_time_used; /* Cumulative microseconds used. */
long long stat_evictedkeys; /* Number of evicted keys (maxmemory) */
long long stat_keyspace_hits; /* Number of successful lookups of keys */
long long stat_keyspace_misses; /* Number of failed lookups of keys */
long long stat_active_defrag_hits; /* number of allocations moved */
long long stat_active_defrag_misses; /* number of allocations scanned but not moved */
long long stat_active_defrag_key_hits; /* number of keys with moved allocations */
long long stat_active_defrag_key_misses;/* number of keys scanned and not moved */
long long stat_active_defrag_scanned; /* number of dictEntries scanned */
size_t stat_peak_memory; /* Max used memory record */
long long stat_fork_time; /* Time needed to perform latest fork() */
double stat_fork_rate; /* Fork rate in GB/sec. */
long long stat_rejected_conn; /* Clients rejected because of maxclients */
long long stat_sync_full; /* Number of full resyncs with slaves. */
long long stat_sync_partial_ok; /* Number of accepted PSYNC requests. */
long long stat_sync_partial_err;/* Number of unaccepted PSYNC requests. */
list *slowlog; /* SLOWLOG list of commands */
long long slowlog_entry_id; /* SLOWLOG current entry ID */
long long slowlog_log_slower_than; /* SLOWLOG time limit (to get logged) */
unsigned long slowlog_max_len; /* SLOWLOG max number of items logged */
struct malloc_stats cron_malloc_stats; /* sampled in serverCron(). */
_Atomic long long stat_net_input_bytes; /* Bytes read from network. */
_Atomic long long stat_net_output_bytes; /* Bytes written to network. */
size_t stat_rdb_cow_bytes; /* Copy on write bytes during RDB saving. */
size_t stat_aof_cow_bytes; /* Copy on write bytes during AOF rewrite. */
size_t stat_module_cow_bytes; /* Copy on write bytes during module fork. */
/* The following two are used to track instantaneous metrics, like
* number of operations per second, network traffic. */
struct {
long long last_sample_time; /* Timestamp of last sample in ms */
long long last_sample_count;/* Count in last sample */
long long samples[STATS_METRIC_SAMPLES];
int idx;
} inst_metric[STATS_METRIC_COUNT];
/* Configuration */
int verbosity; /* Loglevel in redis.conf */
int maxidletime; /* Client timeout in seconds */
int tcpkeepalive; /* Set SO_KEEPALIVE if non-zero. */
int active_expire_enabled; /* Can be disabled for testing purposes. */
int active_expire_effort; /* From 1 (default) to 10, active effort. */
int active_defrag_enabled;
int jemalloc_bg_thread; /* Enable jemalloc background thread */
size_t active_defrag_ignore_bytes; /* minimum amount of fragmentation waste to start active defrag */
int active_defrag_threshold_lower; /* minimum percentage of fragmentation to start active defrag */
int active_defrag_threshold_upper; /* maximum percentage of fragmentation at which we use maximum effort */
int active_defrag_cycle_min; /* minimal effort for defrag in CPU percentage */
int active_defrag_cycle_max; /* maximal effort for defrag in CPU percentage */
unsigned long active_defrag_max_scan_fields; /* maximum number of fields of set/hash/zset/list to process from within the main dict scan */
_Atomic size_t client_max_querybuf_len; /* Limit for client query buffer length */
int dbnum; /* Total number of configured DBs */
int supervised; /* 1 if supervised, 0 otherwise. */
int supervised_mode; /* See SUPERVISED_* */
int daemonize; /* True if running as a daemon */
clientBufferLimitsConfig client_obuf_limits[CLIENT_TYPE_OBUF_COUNT];
/* AOF persistence */
int aof_enabled; /* AOF configuration */
int aof_state; /* AOF_(ON|OFF|WAIT_REWRITE) */
int aof_fsync; /* Kind of fsync() policy */
char *aof_filename; /* Name of the AOF file */
int aof_no_fsync_on_rewrite; /* Don't fsync if a rewrite is in prog. */
int aof_rewrite_perc; /* Rewrite AOF if % growth is > M and... */
off_t aof_rewrite_min_size; /* the AOF file is at least N bytes. */
off_t aof_rewrite_base_size; /* AOF size on latest startup or rewrite. */
off_t aof_current_size; /* AOF current size. */
off_t aof_fsync_offset; /* AOF offset which is already synced to disk. */
int aof_flush_sleep; /* Micros to sleep before flush. (used by tests) */
int aof_rewrite_scheduled; /* Rewrite once BGSAVE terminates. */
pid_t aof_child_pid; /* PID if rewriting process */
list *aof_rewrite_buf_blocks; /* Hold changes during an AOF rewrite. */
sds aof_buf; /* AOF buffer, written before entering the event loop */
int aof_fd; /* File descriptor of currently selected AOF file */
int aof_selected_db; /* Currently selected DB in AOF */
time_t aof_flush_postponed_start; /* UNIX time of postponed AOF flush */
time_t aof_last_fsync; /* UNIX time of last fsync() */
time_t aof_rewrite_time_last; /* Time used by last AOF rewrite run. */
time_t aof_rewrite_time_start; /* Current AOF rewrite start time. */
int aof_lastbgrewrite_status; /* C_OK or C_ERR */
unsigned long aof_delayed_fsync; /* delayed AOF fsync() counter */
int aof_rewrite_incremental_fsync;/* fsync incrementally while aof rewriting? */
int rdb_save_incremental_fsync; /* fsync incrementally while rdb saving? */
int aof_last_write_status; /* C_OK or C_ERR */
int aof_last_write_errno; /* Valid if aof_last_write_status is ERR */
int aof_load_truncated; /* Don't stop on unexpected AOF EOF. */
int aof_use_rdb_preamble; /* Use RDB preamble on AOF rewrites. */
/* AOF pipes used to communicate between parent and child during rewrite. */
int aof_pipe_write_data_to_child;
int aof_pipe_read_data_from_parent;
int aof_pipe_write_ack_to_parent;
int aof_pipe_read_ack_from_child;
int aof_pipe_write_ack_to_child;
int aof_pipe_read_ack_from_parent;
int aof_stop_sending_diff; /* If true stop sending accumulated diffs
to child process. */
sds aof_child_diff; /* AOF diff accumulator child side. */
/* RDB persistence */
long long dirty; /* Changes to DB from the last save */
long long dirty_before_bgsave; /* Used to restore dirty on failed BGSAVE */
pid_t rdb_child_pid; /* PID of RDB saving child */
struct saveparam *saveparams; /* Save points array for RDB */
int saveparamslen; /* Number of saving points */
char *rdb_filename; /* Name of RDB file */
int rdb_compression; /* Use compression in RDB? */
int rdb_checksum; /* Use RDB checksum? */
time_t lastsave; /* Unix time of last successful save */
time_t lastbgsave_try; /* Unix time of last attempted bgsave */
time_t rdb_save_time_last; /* Time used by last RDB save run. */
time_t rdb_save_time_start; /* Current RDB save start time. */
int rdb_bgsave_scheduled; /* BGSAVE when possible if true. */
int rdb_child_type; /* Type of save by active child. */
int lastbgsave_status; /* C_OK or C_ERR */
int stop_writes_on_bgsave_err; /* Don't allow writes if can't BGSAVE */
int rdb_pipe_write; /* RDB pipes used to transfer the rdb */
int rdb_pipe_read; /* data to the parent process in diskless repl. */
connection **rdb_pipe_conns; /* Connections which are currently the */
int rdb_pipe_numconns; /* target of diskless rdb fork child. */
int rdb_pipe_numconns_writing; /* Number of rdb conns with pending writes. */
char *rdb_pipe_buff; /* In diskless replication, this buffer holds data */
int rdb_pipe_bufflen; /* that was read from the the rdb pipe. */
int rdb_key_save_delay; /* Delay in microseconds between keys while
* writing the RDB. (for testings) */
int key_load_delay; /* Delay in microseconds between keys while
* loading aof or rdb. (for testings) */
/* Pipe and data structures for child -> parent info sharing. */
int child_info_pipe[2]; /* Pipe used to write the child_info_data. */
struct {
int process_type; /* AOF or RDB child? */
size_t cow_size; /* Copy on write size. */
unsigned long long magic; /* Magic value to make sure data is valid. */
} child_info_data;
/* Propagation of commands in AOF / replication */
redisOpArray also_propagate; /* Additional command to propagate. */
/* Logging */
char *logfile; /* Path of log file */
int syslog_enabled; /* Is syslog enabled? */
char *syslog_ident; /* Syslog ident */
int syslog_facility; /* Syslog facility */
/* Replication (master) */
char replid[CONFIG_RUN_ID_SIZE+1]; /* My current replication ID. */
char replid2[CONFIG_RUN_ID_SIZE+1]; /* replid inherited from master*/
long long master_repl_offset; /* My current replication offset */
long long second_replid_offset; /* Accept offsets up to this for replid2. */
int slaveseldb; /* Last SELECTed DB in replication output */
int repl_ping_slave_period; /* Master pings the slave every N seconds */
char *repl_backlog; /* Replication backlog for partial syncs */
long long repl_backlog_size; /* Backlog circular buffer size */
long long repl_backlog_histlen; /* Backlog actual data length */
long long repl_backlog_idx; /* Backlog circular buffer current offset,
that is the next byte will'll write to.*/
long long repl_backlog_off; /* Replication "master offset" of first
byte in the replication backlog buffer.*/
time_t repl_backlog_time_limit; /* Time without slaves after the backlog
gets released. */
time_t repl_no_slaves_since; /* We have no slaves since that time.
Only valid if server.slaves len is 0. */
int repl_min_slaves_to_write; /* Min number of slaves to write. */
int repl_min_slaves_max_lag; /* Max lag of <count> slaves to write. */
int repl_good_slaves_count; /* Number of slaves with lag <= max_lag. */
int repl_diskless_sync; /* Master send RDB to slaves sockets directly. */
int repl_diskless_load; /* Slave parse RDB directly from the socket.
* see REPL_DISKLESS_LOAD_* enum */
int repl_diskless_sync_delay; /* Delay to start a diskless repl BGSAVE. */
/* Replication (slave) */
char *masteruser; /* AUTH with this user and masterauth with master */
char *masterauth; /* AUTH with this password with master */
char *masterhost; /* Hostname of master */
int masterport; /* Port of master */
int repl_timeout; /* Timeout after N seconds of master idle */
client *master; /* Client that is master for this slave */
client *cached_master; /* Cached master to be reused for PSYNC. */
int repl_syncio_timeout; /* Timeout for synchronous I/O calls */
int repl_state; /* Replication status if the instance is a slave */
off_t repl_transfer_size; /* Size of RDB to read from master during sync. */
off_t repl_transfer_read; /* Amount of RDB read from master during sync. */
off_t repl_transfer_last_fsync_off; /* Offset when we fsync-ed last time. */
connection *repl_transfer_s; /* Slave -> Master SYNC connection */
int repl_transfer_fd; /* Slave -> Master SYNC temp file descriptor */
char *repl_transfer_tmpfile; /* Slave-> master SYNC temp file name */
time_t repl_transfer_lastio; /* Unix time of the latest read, for timeout */
int repl_serve_stale_data; /* Serve stale data when link is down? */
int repl_slave_ro; /* Slave is read only? */
int repl_slave_ignore_maxmemory; /* If true slaves do not evict. */
time_t repl_down_since; /* Unix time at which link with master went down */
int repl_disable_tcp_nodelay; /* Disable TCP_NODELAY after SYNC? */
int slave_priority; /* Reported in INFO and used by Sentinel. */
int slave_announce_port; /* Give the master this listening port. */
char *slave_announce_ip; /* Give the master this ip address. */
/* The following two fields is where we store master PSYNC replid/offset
* while the PSYNC is in progress. At the end we'll copy the fields into
* the server->master client structure. */
char master_replid[CONFIG_RUN_ID_SIZE+1]; /* Master PSYNC runid. */
long long master_initial_offset; /* Master PSYNC offset. */
int repl_slave_lazy_flush; /* Lazy FLUSHALL before loading DB? */
/* Replication script cache. */
dict *repl_scriptcache_dict; /* SHA1 all slaves are aware of. */
list *repl_scriptcache_fifo; /* First in, first out LRU eviction. */
unsigned int repl_scriptcache_size; /* Max number of elements. */
/* Synchronous replication. */
list *clients_waiting_acks; /* Clients waiting in WAIT command. */
int get_ack_from_slaves; /* If true we send REPLCONF GETACK. */
/* Limits */
unsigned int maxclients; /* Max number of simultaneous clients */
unsigned long long maxmemory; /* Max number of memory bytes to use */
int maxmemory_policy; /* Policy for key eviction */
int maxmemory_samples; /* Pricision of random sampling */
int lfu_log_factor; /* LFU logarithmic counter factor. */
int lfu_decay_time; /* LFU counter decay factor. */
long long proto_max_bulk_len; /* Protocol bulk length maximum size. */
/* Blocked clients */
unsigned int blocked_clients; /* # of clients executing a blocking cmd.*/
unsigned int blocked_clients_by_type[BLOCKED_NUM];
list *unblocked_clients; /* list of clients to unblock before next loop */
list *ready_keys; /* List of readyList structures for BLPOP & co */
/* Client side caching. */
unsigned int tracking_clients; /* # of clients with tracking enabled.*/
int tracking_table_max_fill; /* Max fill percentage. */
/* Sort parameters - qsort_r() is only available under BSD so we
* have to take this state global, in order to pass it to sortCompare() */
int sort_desc;
int sort_alpha;
int sort_bypattern;
int sort_store;
/* Zip structure config, see redis.conf for more information */
size_t hash_max_ziplist_entries;
size_t hash_max_ziplist_value;
size_t set_max_intset_entries;
size_t zset_max_ziplist_entries;
size_t zset_max_ziplist_value;
size_t hll_sparse_max_bytes;
size_t stream_node_max_bytes;
long long stream_node_max_entries;
/* List parameters */
int list_max_ziplist_size;
int list_compress_depth;
/* time cache */
_Atomic time_t unixtime; /* Unix time sampled every cron cycle. */
time_t timezone; /* Cached timezone. As set by tzset(). */
int daylight_active; /* Currently in daylight saving time. */
mstime_t mstime; /* 'unixtime' in milliseconds. */
ustime_t ustime; /* 'unixtime' in microseconds. */
/* Pubsub */
dict *pubsub_channels; /* Map channels to list of subscribed clients */
list *pubsub_patterns; /* A list of pubsub_patterns */
int notify_keyspace_events; /* Events to propagate via Pub/Sub. This is an
xor of NOTIFY_... flags. */
/* Cluster */
int cluster_enabled; /* Is cluster enabled? */
mstime_t cluster_node_timeout; /* Cluster node timeout. */
char *cluster_configfile; /* Cluster auto-generated config file name. */
struct clusterState *cluster; /* State of the cluster */
int cluster_migration_barrier; /* Cluster replicas migration barrier. */
int cluster_slave_validity_factor; /* Slave max data age for failover. */
int cluster_require_full_coverage; /* If true, put the cluster down if
there is at least an uncovered slot.*/
int cluster_slave_no_failover; /* Prevent slave from starting a failover
if the master is in failure state. */
char *cluster_announce_ip; /* IP address to announce on cluster bus. */
int cluster_announce_port; /* base port to announce on cluster bus. */
int cluster_announce_bus_port; /* bus port to announce on cluster bus. */
int cluster_module_flags; /* Set of flags that Redis modules are able
to set in order to suppress certain
native Redis Cluster features. Check the
REDISMODULE_CLUSTER_FLAG_*. */
/* Scripting */
lua_State *lua; /* The Lua interpreter. We use just one for all clients */
client *lua_client; /* The "fake client" to query Redis from Lua */
client *lua_caller; /* The client running EVAL right now, or NULL */
char* lua_cur_script; /* SHA1 of the script currently running, or NULL */
dict *lua_scripts; /* A dictionary of SHA1 -> Lua scripts */
unsigned long long lua_scripts_mem; /* Cached scripts' memory + oh */
mstime_t lua_time_limit; /* Script timeout in milliseconds */
mstime_t lua_time_start; /* Start time of script, milliseconds time */
int lua_write_dirty; /* True if a write command was called during the
execution of the current script. */
int lua_random_dirty; /* True if a random command was called during the
execution of the current script. */
int lua_replicate_commands; /* True if we are doing single commands repl. */
int lua_multi_emitted;/* True if we already proagated MULTI. */
int lua_repl; /* Script replication flags for redis.set_repl(). */
int lua_timedout; /* True if we reached the time limit for script
execution. */
int lua_kill; /* Kill the script if true. */
int lua_always_replicate_commands; /* Default replication type. */
/* Lazy free */
int lazyfree_lazy_eviction;
int lazyfree_lazy_expire;
int lazyfree_lazy_server_del;
/* Latency monitor */
long long latency_monitor_threshold;
dict *latency_events;
/* ACLs */
char *acl_filename; /* ACL Users file. NULL if not configured. */
/* Assert & bug reporting */
const char *assert_failed;
const char *assert_file;
int assert_line;
int bug_report_start; /* True if bug report header was already logged. */
int watchdog_period; /* Software watchdog period in ms. 0 = off */
/* System hardware info */
size_t system_memory_size; /* Total memory in system as reported by OS */
/* TLS Configuration */
int tls_cluster;
int tls_replication;
int tls_auth_clients;
redisTLSContextConfig tls_ctx_config;
};
客戶端
數據結構
typedef struct client {
uint64_t id; /* Client incremental unique ID. */
connection *conn;
int resp; /* RESP protocol version. Can be 2 or 3. */
redisDb *db; /* Pointer to currently SELECTed DB. */
robj *name; /* As set by CLIENT SETNAME. */
sds querybuf; /* Buffer we use to accumulate client queries. */
size_t qb_pos; /* The position we have read in querybuf. */
sds pending_querybuf; /* If this client is flagged as master, this buffer
represents the yet not applied portion of the
replication stream that we are receiving from
the master. */
size_t querybuf_peak; /* Recent (100ms or more) peak of querybuf size. */
int argc; /* Num of arguments of current command. */
robj **argv; /* Arguments of current command. */
struct redisCommand *cmd, *lastcmd; /* Last command executed. */
user *user; /* User associated with this connection. If the
user is set to NULL the connection can do
anything (admin). */
int reqtype; /* Request protocol type: PROTO_REQ_* */
int multibulklen; /* Number of multi bulk arguments left to read. */
long bulklen; /* Length of bulk argument in multi bulk request. */
list *reply; /* List of reply objects to send to the client. */
unsigned long long reply_bytes; /* Tot bytes of objects in reply list. */
size_t sentlen; /* Amount of bytes already sent in the current
buffer or object being sent. */
time_t ctime; /* Client creation time. */
time_t lastinteraction; /* Time of the last interaction, used for timeout */
time_t obuf_soft_limit_reached_time;
uint64_t flags; /* Client flags: CLIENT_* macros. */
int authenticated; /* Needed when the default user requires auth. */
int replstate; /* Replication state if this is a slave. */
int repl_put_online_on_ack; /* Install slave write handler on first ACK. */
int repldbfd; /* Replication DB file descriptor. */
off_t repldboff; /* Replication DB file offset. */
off_t repldbsize; /* Replication DB file size. */
sds replpreamble; /* Replication DB preamble. */
long long read_reploff; /* Read replication offset if this is a master. */
long long reploff; /* Applied replication offset if this is a master. */
long long repl_ack_off; /* Replication ack offset, if this is a slave. */
long long repl_ack_time;/* Replication ack time, if this is a slave. */
long long psync_initial_offset; /* FULLRESYNC reply offset other slaves
copying this slave output buffer
should use. */
char replid[CONFIG_RUN_ID_SIZE+1]; /* Master replication ID (if master). */
int slave_listening_port; /* As configured with: SLAVECONF listening-port */
char slave_ip[NET_IP_STR_LEN]; /* Optionally given by REPLCONF ip-address */
int slave_capa; /* Slave capabilities: SLAVE_CAPA_* bitwise OR. */
multiState mstate; /* MULTI/EXEC state */
int btype; /* Type of blocking op if CLIENT_BLOCKED. */
blockingState bpop; /* blocking state */
long long woff; /* Last write global replication offset. */
list *watched_keys; /* Keys WATCHED for MULTI/EXEC CAS */
dict *pubsub_channels; /* channels a client is interested in (SUBSCRIBE) */
list *pubsub_patterns; /* patterns a client is interested in (SUBSCRIBE) */
sds peerid; /* Cached peer ID. */
listNode *client_list_node; /* list node in client list */
/* If this client is in tracking mode and this field is non zero,
* invalidation messages for keys fetched by this client will be send to
* the specified client ID. */
uint64_t client_tracking_redirection;
/* Response buffer */
int bufpos;
char buf[PROTO_REPLY_CHUNK_BYTES];
} client;