redict/src/server.h

1846 lines
80 KiB
C
Raw Normal View History

/*
* Copyright (c) 2009-2012, Salvatore Sanfilippo <antirez at gmail dot com>
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of Redis nor the names of its contributors may be used
* to endorse or promote products derived from this software without
* specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
#ifndef __REDIS_H
#define __REDIS_H
#include "fmacros.h"
#include "config.h"
#include "solarisfixes.h"
#include "rio.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>
#include <limits.h>
#include <unistd.h>
#include <errno.h>
#include <inttypes.h>
2010-07-05 14:14:48 -04:00
#include <pthread.h>
2010-12-09 11:10:21 -05:00
#include <syslog.h>
2011-03-29 11:51:15 -04:00
#include <netinet/in.h>
#include <lua.h>
#include <signal.h>
typedef long long mstime_t; /* millisecond time type. */
#include "ae.h" /* Event driven programming library */
#include "sds.h" /* Dynamic safe strings */
#include "dict.h" /* Hash tables */
#include "adlist.h" /* Linked lists */
#include "zmalloc.h" /* total memory usage aware version of malloc/free */
#include "anet.h" /* Networking the easy way */
#include "ziplist.h" /* Compact list data structure */
#include "intset.h" /* Compact integer set structure */
#include "version.h" /* Version macro */
#include "util.h" /* Misc functions useful in many places */
#include "latency.h" /* Latency monitor API */
2016-01-29 06:08:10 -05:00
#include "sparkline.h" /* ASCII graphs API */
#include "quicklist.h"
/* Following includes allow test functions to be called from Redis main() */
#include "zipmap.h"
#include "sha1.h"
#include "endianconv.h"
#include "crc64.h"
/* Error codes */
#define C_OK 0
#define C_ERR -1
/* Static server configuration */
#define CONFIG_DEFAULT_HZ 10 /* Time interrupt calls/sec. */
2015-07-27 03:41:48 -04:00
#define CONFIG_MIN_HZ 1
#define CONFIG_MAX_HZ 500
#define CONFIG_DEFAULT_SERVER_PORT 6379 /* TCP port */
#define CONFIG_DEFAULT_TCP_BACKLOG 511 /* TCP listen backlog */
#define CONFIG_DEFAULT_CLIENT_TIMEOUT 0 /* default client timeout: infinite */
#define CONFIG_DEFAULT_DBNUM 16
2015-07-27 03:41:48 -04:00
#define CONFIG_MAX_LINE 1024
#define CRON_DBS_PER_CALL 16
#define NET_MAX_WRITES_PER_EVENT (1024*64)
#define PROTO_SHARED_SELECT_CMDS 10
#define OBJ_SHARED_INTEGERS 10000
#define OBJ_SHARED_BULKHDR_LEN 32
#define LOG_MAX_LEN 1024 /* Default maximum length of syslog messages */
#define AOF_REWRITE_PERC 100
#define AOF_REWRITE_MIN_SIZE (64*1024*1024)
#define AOF_REWRITE_ITEMS_PER_CMD 64
2016-08-09 05:07:32 -04:00
#define AOF_READ_DIFF_INTERVAL_BYTES (1024*10)
2015-07-27 03:41:48 -04:00
#define CONFIG_DEFAULT_SLOWLOG_LOG_SLOWER_THAN 10000
#define CONFIG_DEFAULT_SLOWLOG_MAX_LEN 128
#define CONFIG_DEFAULT_MAX_CLIENTS 10000
2015-07-27 03:41:48 -04:00
#define CONFIG_AUTHPASS_MAX_LEN 512
#define CONFIG_DEFAULT_SLAVE_PRIORITY 100
2015-07-27 03:41:48 -04:00
#define CONFIG_DEFAULT_REPL_TIMEOUT 60
#define CONFIG_DEFAULT_REPL_PING_SLAVE_PERIOD 10
#define CONFIG_RUN_ID_SIZE 40
#define RDB_EOF_MARK_SIZE 40
#define CONFIG_DEFAULT_REPL_BACKLOG_SIZE (1024*1024) /* 1mb */
#define CONFIG_DEFAULT_REPL_BACKLOG_TIME_LIMIT (60*60) /* 1 hour */
2015-07-27 03:41:48 -04:00
#define CONFIG_REPL_BACKLOG_MIN_SIZE (1024*16) /* 16k */
#define CONFIG_BGSAVE_RETRY_DELAY 5 /* Wait a few secs before trying again. */
#define CONFIG_DEFAULT_PID_FILE "/var/run/redis.pid"
#define CONFIG_DEFAULT_SYSLOG_IDENT "redis"
#define CONFIG_DEFAULT_CLUSTER_CONFIG_FILE "nodes.conf"
#define CONFIG_DEFAULT_CLUSTER_ANNOUNCE_IP NULL /* Auto detect. */
#define CONFIG_DEFAULT_CLUSTER_ANNOUNCE_PORT 0 /* Use server.port */
#define CONFIG_DEFAULT_CLUSTER_ANNOUNCE_BUS_PORT 0 /* Use +10000 offset. */
#define CONFIG_DEFAULT_DAEMONIZE 0
#define CONFIG_DEFAULT_UNIX_SOCKET_PERM 0
#define CONFIG_DEFAULT_TCP_KEEPALIVE 300
#define CONFIG_DEFAULT_PROTECTED_MODE 1
#define CONFIG_DEFAULT_LOGFILE ""
#define CONFIG_DEFAULT_SYSLOG_ENABLED 0
#define CONFIG_DEFAULT_STOP_WRITES_ON_BGSAVE_ERROR 1
#define CONFIG_DEFAULT_RDB_COMPRESSION 1
#define CONFIG_DEFAULT_RDB_CHECKSUM 1
#define CONFIG_DEFAULT_RDB_FILENAME "dump.rdb"
#define CONFIG_DEFAULT_REPL_DISKLESS_SYNC 0
#define CONFIG_DEFAULT_REPL_DISKLESS_SYNC_DELAY 5
#define CONFIG_DEFAULT_SLAVE_SERVE_STALE_DATA 1
#define CONFIG_DEFAULT_SLAVE_READ_ONLY 1
#define CONFIG_DEFAULT_SLAVE_ANNOUNCE_IP NULL
#define CONFIG_DEFAULT_SLAVE_ANNOUNCE_PORT 0
#define CONFIG_DEFAULT_REPL_DISABLE_TCP_NODELAY 0
#define CONFIG_DEFAULT_MAXMEMORY 0
#define CONFIG_DEFAULT_MAXMEMORY_SAMPLES 5
#define CONFIG_DEFAULT_LFU_LOG_FACTOR 10
#define CONFIG_DEFAULT_LFU_DECAY_TIME 1
#define CONFIG_DEFAULT_AOF_FILENAME "appendonly.aof"
#define CONFIG_DEFAULT_AOF_NO_FSYNC_ON_REWRITE 0
#define CONFIG_DEFAULT_AOF_LOAD_TRUNCATED 1
#define CONFIG_DEFAULT_ACTIVE_REHASHING 1
#define CONFIG_DEFAULT_AOF_REWRITE_INCREMENTAL_FSYNC 1
#define CONFIG_DEFAULT_MIN_SLAVES_TO_WRITE 0
#define CONFIG_DEFAULT_MIN_SLAVES_MAX_LAG 10
2015-07-27 03:41:48 -04:00
#define NET_IP_STR_LEN 46 /* INET6_ADDRSTRLEN is 46, but we need to be sure */
#define NET_PEER_ID_LEN (NET_IP_STR_LEN+32) /* Must be enough for ip:port */
#define CONFIG_BINDADDR_MAX 16
#define CONFIG_MIN_RESERVED_FDS 32
#define CONFIG_DEFAULT_LATENCY_MONITOR_THRESHOLD 0
#define CONFIG_DEFAULT_SLAVE_LAZY_FLUSH 0
#define CONFIG_DEFAULT_LAZYFREE_LAZY_EVICTION 0
#define CONFIG_DEFAULT_LAZYFREE_LAZY_EXPIRE 0
#define CONFIG_DEFAULT_LAZYFREE_LAZY_SERVER_DEL 0
2013-08-06 06:55:49 -04:00
#define ACTIVE_EXPIRE_CYCLE_LOOKUPS_PER_LOOP 20 /* Loopkups per loop. */
#define ACTIVE_EXPIRE_CYCLE_FAST_DURATION 1000 /* Microseconds */
#define ACTIVE_EXPIRE_CYCLE_SLOW_TIME_PERC 25 /* CPU max % for keys collection */
#define ACTIVE_EXPIRE_CYCLE_SLOW 0
#define ACTIVE_EXPIRE_CYCLE_FAST 1
/* Instantaneous metrics tracking. */
2015-07-27 03:41:48 -04:00
#define STATS_METRIC_SAMPLES 16 /* Number of samples per metric. */
#define STATS_METRIC_COMMAND 0 /* Number of commands executed. */
#define STATS_METRIC_NET_INPUT 1 /* Bytes read to network .*/
#define STATS_METRIC_NET_OUTPUT 2 /* Bytes written to network. */
#define STATS_METRIC_COUNT 3
/* Protocol and I/O related defines */
2015-07-27 03:41:48 -04:00
#define PROTO_MAX_QUERYBUF_LEN (1024*1024*1024) /* 1GB max query buffer. */
#define PROTO_IOBUF_LEN (1024*16) /* Generic I/O buffer size */
#define PROTO_REPLY_CHUNK_BYTES (16*1024) /* 16k output buffer */
#define PROTO_INLINE_MAX_SIZE (1024*64) /* Max size of inline reads */
#define PROTO_MBULK_BIG_ARG (1024*32)
#define LONG_STR_SIZE 21 /* Bytes needed for long -> str + '\0' */
2015-07-27 03:41:48 -04:00
#define AOF_AUTOSYNC_BYTES (1024*1024*32) /* fdatasync every 32MB */
/* When configuring the server eventloop, we setup it so that the total number
* of file descriptors we can handle are server.maxclients + RESERVED_FDS +
* a few more to stay safe. Since RESERVED_FDS defaults to 32, we add 96
* in order to make sure of not over provisioning more than 128 fds. */
#define CONFIG_FDSET_INCR (CONFIG_MIN_RESERVED_FDS+96)
2011-10-31 06:13:28 -04:00
/* Hash table parameters */
2015-07-27 03:41:48 -04:00
#define HASHTABLE_MIN_FILL 10 /* Minimal hash table fill 10% */
/* Command flags. Please check the command table defined in the redis.c file
* for more information about the meaning of every flag. */
#define CMD_WRITE (1<<0) /* "w" flag */
#define CMD_READONLY (1<<1) /* "r" flag */
#define CMD_DENYOOM (1<<2) /* "m" flag */
#define CMD_MODULE (1<<3) /* Command exported by module. */
#define CMD_ADMIN (1<<4) /* "a" flag */
#define CMD_PUBSUB (1<<5) /* "p" flag */
#define CMD_NOSCRIPT (1<<6) /* "s" flag */
#define CMD_RANDOM (1<<7) /* "R" flag */
#define CMD_SORT_FOR_SCRIPT (1<<8) /* "S" flag */
#define CMD_LOADING (1<<9) /* "l" flag */
#define CMD_STALE (1<<10) /* "t" flag */
#define CMD_SKIP_MONITOR (1<<11) /* "M" flag */
#define CMD_ASKING (1<<12) /* "k" flag */
#define CMD_FAST (1<<13) /* "F" flag */
#define CMD_MODULE_GETKEYS (1<<14) /* Use the modules getkeys interface. */
#define CMD_MODULE_NO_CLUSTER (1<<15) /* Deny on Redis Cluster. */
/* AOF states */
2015-07-27 03:41:48 -04:00
#define AOF_OFF 0 /* AOF is off */
#define AOF_ON 1 /* AOF is on */
#define AOF_WAIT_REWRITE 2 /* AOF waits rewrite to start appending */
/* Client flags */
2015-07-27 03:41:48 -04:00
#define CLIENT_SLAVE (1<<0) /* This client is a slave server */
#define CLIENT_MASTER (1<<1) /* This client is a master server */
#define CLIENT_MONITOR (1<<2) /* This client is a slave monitor, see MONITOR */
#define CLIENT_MULTI (1<<3) /* This client is in a MULTI context */
#define CLIENT_BLOCKED (1<<4) /* The client is waiting in a blocking operation */
#define CLIENT_DIRTY_CAS (1<<5) /* Watched keys modified. EXEC will fail. */
#define CLIENT_CLOSE_AFTER_REPLY (1<<6) /* Close after writing entire reply. */
#define CLIENT_UNBLOCKED (1<<7) /* This client was unblocked and is stored in
server.unblocked_clients */
2015-07-27 03:41:48 -04:00
#define CLIENT_LUA (1<<8) /* This is a non connected client used by Lua */
#define CLIENT_ASKING (1<<9) /* Client issued the ASKING command */
#define CLIENT_CLOSE_ASAP (1<<10)/* Close this client ASAP */
#define CLIENT_UNIX_SOCKET (1<<11) /* Client connected via Unix domain socket */
#define CLIENT_DIRTY_EXEC (1<<12) /* EXEC will fail for errors while queueing */
#define CLIENT_MASTER_FORCE_REPLY (1<<13) /* Queue replies even if is master */
#define CLIENT_FORCE_AOF (1<<14) /* Force AOF propagation of current cmd. */
#define CLIENT_FORCE_REPL (1<<15) /* Force replication of current cmd. */
#define CLIENT_PRE_PSYNC (1<<16) /* Instance don't understand PSYNC. */
#define CLIENT_READONLY (1<<17) /* Cluster client is in read-only state. */
#define CLIENT_PUBSUB (1<<18) /* Client is in Pub/Sub mode. */
#define CLIENT_PREVENT_AOF_PROP (1<<19) /* Don't propagate to AOF. */
#define CLIENT_PREVENT_REPL_PROP (1<<20) /* Don't propagate to slaves. */
#define CLIENT_PREVENT_PROP (CLIENT_PREVENT_AOF_PROP|CLIENT_PREVENT_REPL_PROP)
#define CLIENT_PENDING_WRITE (1<<21) /* Client has output to send but a write
handler is yet not installed. */
#define CLIENT_REPLY_OFF (1<<22) /* Don't send replies to client. */
#define CLIENT_REPLY_SKIP_NEXT (1<<23) /* Set CLIENT_REPLY_SKIP for next cmd */
#define CLIENT_REPLY_SKIP (1<<24) /* Don't send just this reply. */
#define CLIENT_LUA_DEBUG (1<<25) /* Run EVAL in debug mode. */
2015-11-06 10:19:59 -05:00
#define CLIENT_LUA_DEBUG_SYNC (1<<26) /* EVAL debugging without fork() */
2016-03-06 07:44:24 -05:00
#define CLIENT_MODULE (1<<27) /* Non connected client used by some module. */
/* Client block type (btype field in client structure)
2015-07-27 03:41:48 -04:00
* if CLIENT_BLOCKED flag is set. */
#define BLOCKED_NONE 0 /* Not blocked, no CLIENT_BLOCKED flag set. */
#define BLOCKED_LIST 1 /* BLPOP & co. */
#define BLOCKED_WAIT 2 /* WAIT for synchronous replication. */
/* Client request types */
2015-07-27 03:41:48 -04:00
#define PROTO_REQ_INLINE 1
#define PROTO_REQ_MULTIBULK 2
/* Client classes for client limits, currently used only for
* the max-client-output-buffer limit implementation. */
2015-07-27 03:41:48 -04:00
#define CLIENT_TYPE_NORMAL 0 /* Normal req-reply clients + MONITORs */
#define CLIENT_TYPE_SLAVE 1 /* Slaves. */
#define CLIENT_TYPE_PUBSUB 2 /* Clients subscribed to PubSub channels. */
2015-07-28 10:58:04 -04:00
#define CLIENT_TYPE_MASTER 3 /* Master. */
#define CLIENT_TYPE_OBUF_COUNT 3 /* Number of clients to expose to output
buffer configuration. Just the first
three: normal, slave, pubsub. */
2015-07-27 03:41:48 -04:00
/* Slave replication state. Used in server.repl_state for slaves to remember
* what to do next. */
#define REPL_STATE_NONE 0 /* No active replication */
#define REPL_STATE_CONNECT 1 /* Must connect to master */
#define REPL_STATE_CONNECTING 2 /* Connecting to master */
2015-10-15 04:20:09 -04:00
/* --- Handshake states, must be ordered --- */
2015-07-27 03:41:48 -04:00
#define REPL_STATE_RECEIVE_PONG 3 /* Wait for PING reply */
#define REPL_STATE_SEND_AUTH 4 /* Send AUTH to master */
#define REPL_STATE_RECEIVE_AUTH 5 /* Wait for AUTH reply */
#define REPL_STATE_SEND_PORT 6 /* Send REPLCONF listening-port */
#define REPL_STATE_RECEIVE_PORT 7 /* Wait for REPLCONF reply */
#define REPL_STATE_SEND_IP 8 /* Send REPLCONF ip-address */
#define REPL_STATE_RECEIVE_IP 9 /* Wait for REPLCONF reply */
#define REPL_STATE_SEND_CAPA 10 /* Send REPLCONF capa */
#define REPL_STATE_RECEIVE_CAPA 11 /* Wait for REPLCONF reply */
#define REPL_STATE_SEND_PSYNC 12 /* Send PSYNC */
#define REPL_STATE_RECEIVE_PSYNC 13 /* Wait for PSYNC reply */
2015-10-15 04:20:09 -04:00
/* --- End of handshake states --- */
#define REPL_STATE_TRANSFER 14 /* Receiving .rdb from master */
#define REPL_STATE_CONNECTED 15 /* Connected to master */
2015-07-27 03:41:48 -04:00
/* State of slaves from the POV of the master. Used in client->replstate.
* In SEND_BULK and ONLINE state the slave receives new updates
2015-07-27 03:41:48 -04:00
* in its output queue. In the WAIT_BGSAVE states instead the server is waiting
* to start the next background saving in order to send updates to it. */
2015-07-27 03:41:48 -04:00
#define SLAVE_STATE_WAIT_BGSAVE_START 6 /* We need to produce a new RDB file. */
#define SLAVE_STATE_WAIT_BGSAVE_END 7 /* Waiting RDB file creation to finish. */
#define SLAVE_STATE_SEND_BULK 8 /* Sending RDB file to slave. */
#define SLAVE_STATE_ONLINE 9 /* RDB file transmitted, sending just updates. */
/* Slave capabilities. */
#define SLAVE_CAPA_NONE 0
#define SLAVE_CAPA_EOF (1<<0) /* Can parse the RDB EOF streaming format. */
/* Synchronous read timeout - slave side */
2015-07-27 03:41:48 -04:00
#define CONFIG_REPL_SYNCIO_TIMEOUT 5
/* List related stuff */
2015-07-27 03:41:48 -04:00
#define LIST_HEAD 0
#define LIST_TAIL 1
/* Sort operations */
2015-07-27 03:41:48 -04:00
#define SORT_OP_GET 0
/* Log levels */
2015-07-27 03:41:48 -04:00
#define LL_DEBUG 0
#define LL_VERBOSE 1
#define LL_NOTICE 2
#define LL_WARNING 3
#define LL_RAW (1<<10) /* Modifier to log without timestamp */
#define CONFIG_DEFAULT_VERBOSITY LL_NOTICE
/* Supervision options */
2015-07-27 03:41:48 -04:00
#define SUPERVISED_NONE 0
#define SUPERVISED_AUTODETECT 1
#define SUPERVISED_SYSTEMD 2
#define SUPERVISED_UPSTART 3
/* Anti-warning macro... */
2015-07-27 03:41:48 -04:00
#define UNUSED(V) ((void) V)
#define ZSKIPLIST_MAXLEVEL 32 /* Should be enough for 2^32 elements */
#define ZSKIPLIST_P 0.25 /* Skiplist P = 1/4 */
/* Append only defines */
#define AOF_FSYNC_NO 0
#define AOF_FSYNC_ALWAYS 1
#define AOF_FSYNC_EVERYSEC 2
#define CONFIG_DEFAULT_AOF_FSYNC AOF_FSYNC_EVERYSEC
/* Zip structure related defaults */
#define OBJ_HASH_MAX_ZIPLIST_ENTRIES 512
#define OBJ_HASH_MAX_ZIPLIST_VALUE 64
#define OBJ_SET_MAX_INTSET_ENTRIES 512
#define OBJ_ZSET_MAX_ZIPLIST_ENTRIES 128
#define OBJ_ZSET_MAX_ZIPLIST_VALUE 64
/* List defaults */
#define OBJ_LIST_MAX_ZIPLIST_SIZE -2
#define OBJ_LIST_COMPRESS_DEPTH 0
/* HyperLogLog defines */
#define CONFIG_DEFAULT_HLL_SPARSE_MAX_BYTES 3000
/* Sets operations codes */
2015-07-27 03:41:48 -04:00
#define SET_OP_UNION 0
#define SET_OP_DIFF 1
#define SET_OP_INTER 2
/* Redis maxmemory strategies. Instead of using just incremental number
* for this defines, we use a set of flags so that testing for certain
* properties common to multiple policies is faster. */
#define MAXMEMORY_FLAG_LRU (1<<0)
#define MAXMEMORY_FLAG_LFU (1<<1)
#define MAXMEMORY_FLAG_ALLKEYS (1<<2)
#define MAXMEMORY_FLAG_NO_SHARED_INTEGERS \
(MAXMEMORY_FLAG_LRU|MAXMEMORY_FLAG_LFU)
#define MAXMEMORY_VOLATILE_LRU ((0<<8)|MAXMEMORY_FLAG_LRU)
#define MAXMEMORY_VOLATILE_LFU ((1<<8)|MAXMEMORY_FLAG_LFU)
#define MAXMEMORY_VOLATILE_TTL (2<<8)
#define MAXMEMORY_VOLATILE_RANDOM (3<<8)
#define MAXMEMORY_ALLKEYS_LRU ((4<<8)|MAXMEMORY_FLAG_LRU|MAXMEMORY_FLAG_ALLKEYS)
#define MAXMEMORY_ALLKEYS_LFU ((5<<8)|MAXMEMORY_FLAG_LFU|MAXMEMORY_FLAG_ALLKEYS)
#define MAXMEMORY_ALLKEYS_RANDOM ((6<<8)|MAXMEMORY_FLAG_ALLKEYS)
#define MAXMEMORY_NO_EVICTION (7<<8)
2015-07-27 03:41:48 -04:00
#define CONFIG_DEFAULT_MAXMEMORY_POLICY MAXMEMORY_NO_EVICTION
2011-05-06 11:21:27 -04:00
/* Scripting */
2015-07-27 03:41:48 -04:00
#define LUA_SCRIPT_TIME_LIMIT 5000 /* milliseconds */
2011-05-06 11:21:27 -04:00
/* Units */
#define UNIT_SECONDS 0
#define UNIT_MILLISECONDS 1
/* SHUTDOWN flags */
#define SHUTDOWN_NOFLAGS 0 /* No flags. */
#define SHUTDOWN_SAVE 1 /* Force SAVE on SHUTDOWN even if no save
points are configured. */
#define SHUTDOWN_NOSAVE 2 /* Don't SAVE on SHUTDOWN. */
/* Command call flags, see call() function */
2015-07-27 03:41:48 -04:00
#define CMD_CALL_NONE 0
#define CMD_CALL_SLOWLOG (1<<0)
#define CMD_CALL_STATS (1<<1)
#define CMD_CALL_PROPAGATE_AOF (1<<2)
#define CMD_CALL_PROPAGATE_REPL (1<<3)
#define CMD_CALL_PROPAGATE (CMD_CALL_PROPAGATE_AOF|CMD_CALL_PROPAGATE_REPL)
2015-07-27 03:41:48 -04:00
#define CMD_CALL_FULL (CMD_CALL_SLOWLOG | CMD_CALL_STATS | CMD_CALL_PROPAGATE)
2012-02-28 10:17:00 -05:00
/* Command propagation flags, see propagate() function */
2015-07-27 03:41:48 -04:00
#define PROPAGATE_NONE 0
#define PROPAGATE_AOF 1
#define PROPAGATE_REPL 2
2012-02-28 10:17:00 -05:00
/* RDB active child save type. */
2015-07-27 03:41:48 -04:00
#define RDB_CHILD_TYPE_NONE 0
#define RDB_CHILD_TYPE_DISK 1 /* RDB is written to disk. */
#define RDB_CHILD_TYPE_SOCKET 2 /* RDB is written to slave socket. */
/* Keyspace changes notification classes. Every class is associated with a
* character for configuration purposes. */
2015-07-27 03:41:48 -04:00
#define NOTIFY_KEYSPACE (1<<0) /* K */
#define NOTIFY_KEYEVENT (1<<1) /* E */
#define NOTIFY_GENERIC (1<<2) /* g */
#define NOTIFY_STRING (1<<3) /* $ */
#define NOTIFY_LIST (1<<4) /* l */
#define NOTIFY_SET (1<<5) /* s */
#define NOTIFY_HASH (1<<6) /* h */
#define NOTIFY_ZSET (1<<7) /* z */
#define NOTIFY_EXPIRED (1<<8) /* x */
#define NOTIFY_EVICTED (1<<9) /* e */
#define NOTIFY_ALL (NOTIFY_GENERIC | NOTIFY_STRING | NOTIFY_LIST | NOTIFY_SET | NOTIFY_HASH | NOTIFY_ZSET | NOTIFY_EXPIRED | NOTIFY_EVICTED) /* A */
/* Get the first bind addr or NULL */
2015-07-27 03:41:48 -04:00
#define NET_FIRST_BIND_ADDR (server.bindaddr_count ? server.bindaddr[0] : NULL)
/* Using the following macro you can run code inside serverCron() with the
* specified period, specified in milliseconds.
* The actual resolution depends on server.hz. */
#define run_with_period(_ms_) if ((_ms_ <= 1000/server.hz) || !(server.cronloops%((_ms_)/(1000/server.hz))))
/* We can print the stacktrace, so our assert is defined this way: */
2015-07-26 09:29:53 -04:00
#define serverAssertWithInfo(_c,_o,_e) ((_e)?(void)0 : (_serverAssertWithInfo(_c,_o,#_e,__FILE__,__LINE__),_exit(1)))
#define serverAssert(_e) ((_e)?(void)0 : (_serverAssert(#_e,__FILE__,__LINE__),_exit(1)))
2015-07-27 03:41:48 -04:00
#define serverPanic(_e) _serverPanic(#_e,__FILE__,__LINE__),_exit(1)
/*-----------------------------------------------------------------------------
* Data types
*----------------------------------------------------------------------------*/
/* A redis object, that is a type able to hold a string / list / set */
/* The actual Redis Object */
#define OBJ_STRING 0
#define OBJ_LIST 1
#define OBJ_SET 2
#define OBJ_ZSET 3
#define OBJ_HASH 4
/* The "module" object type is a special one that signals that the object
* is one directly managed by a Redis module. In this case the value points
* to a moduleValue struct, which contains the object value (which is only
* handled by the module itself) and the RedisModuleType struct which lists
* function pointers in order to serialize, deserialize, AOF-rewrite and
* free the object.
*
* Inside the RDB file, module types are encoded as OBJ_MODULE followed
* by a 64 bit module type ID, which has a 54 bits module-specific signature
* in order to dispatch the loading to the right module, plus a 10 bits
* encoding version. */
#define OBJ_MODULE 5
/* Extract encver / signature from a module type ID. */
#define REDISMODULE_TYPE_ENCVER_BITS 10
#define REDISMODULE_TYPE_ENCVER_MASK ((1<<REDISMODULE_TYPE_ENCVER_BITS)-1)
#define REDISMODULE_TYPE_ENCVER(id) (id & REDISMODULE_TYPE_ENCVER_MASK)
#define REDISMODULE_TYPE_SIGN(id) ((id & ~((uint64_t)REDISMODULE_TYPE_ENCVER_MASK)) >>REDISMODULE_TYPE_ENCVER_BITS)
struct RedisModule;
struct RedisModuleIO;
struct RedisModuleDigest;
struct redisObject;
/* Each module type implementation should export a set of methods in order
* to serialize and deserialize the value in the RDB file, rewrite the AOF
* log, create the digest for "DEBUG DIGEST", and free the value when a key
* is deleted. */
typedef void *(*moduleTypeLoadFunc)(struct RedisModuleIO *io, int encver);
typedef void (*moduleTypeSaveFunc)(struct RedisModuleIO *io, void *value);
typedef void (*moduleTypeRewriteFunc)(struct RedisModuleIO *io, struct redisObject *key, void *value);
typedef void (*moduleTypeDigestFunc)(struct RedisModuleDigest *digest, void *value);
typedef void (*moduleTypeFreeFunc)(void *value);
/* The module type, which is referenced in each value of a given type, defines
* the methods and links to the module exporting the type. */
typedef struct RedisModuleType {
uint64_t id; /* Higher 54 bits of type ID + 10 lower bits of encoding ver. */
struct RedisModule *module;
moduleTypeLoadFunc rdb_load;
moduleTypeSaveFunc rdb_save;
moduleTypeRewriteFunc aof_rewrite;
moduleTypeDigestFunc digest;
moduleTypeFreeFunc free;
char name[10]; /* 9 bytes name + null term. Charset: A-Z a-z 0-9 _- */
} moduleType;
/* In Redis objects 'robj' structures of type OBJ_MODULE, the value pointer
* is set to the following structure, referencing the moduleType structure
* in order to work with the value, and at the same time providing a raw
* pointer to the value, as created by the module commands operating with
* the module type.
*
* So for example in order to free such a value, it is possible to use
* the following code:
*
* if (robj->type == OBJ_MODULE) {
* moduleValue *mt = robj->ptr;
* mt->type->free(mt->value);
* zfree(mt); // We need to release this in-the-middle struct as well.
* }
*/
typedef struct moduleValue {
moduleType *type;
void *value;
} moduleValue;
/* This is a wrapper for the 'rio' streams used inside rdb.c in Redis, so that
* the user does not have to take the total count of the written bytes nor
* to care about error conditions. */
typedef struct RedisModuleIO {
size_t bytes; /* Bytes read / written so far. */
rio *rio; /* Rio stream. */
moduleType *type; /* Module type doing the operation. */
int error; /* True if error condition happened. */
} RedisModuleIO;
#define moduleInitIOContext(iovar,mtype,rioptr) do { \
iovar.rio = rioptr; \
iovar.type = mtype; \
iovar.bytes = 0; \
iovar.error = 0; \
} while(0);
/* Objects encoding. Some kind of objects like Strings and Hashes can be
* internally represented in multiple ways. The 'encoding' field of the object
* is set to one of this fields for this object. */
#define OBJ_ENCODING_RAW 0 /* Raw representation */
#define OBJ_ENCODING_INT 1 /* Encoded as integer */
#define OBJ_ENCODING_HT 2 /* Encoded as hash table */
#define OBJ_ENCODING_ZIPMAP 3 /* Encoded as zipmap */
#define OBJ_ENCODING_LINKEDLIST 4 /* Encoded as regular linked list */
#define OBJ_ENCODING_ZIPLIST 5 /* Encoded as ziplist */
#define OBJ_ENCODING_INTSET 6 /* Encoded as intset */
#define OBJ_ENCODING_SKIPLIST 7 /* Encoded as skiplist */
#define OBJ_ENCODING_EMBSTR 8 /* Embedded sds string encoding */
#define OBJ_ENCODING_QUICKLIST 9 /* Encoded as linked list of ziplists */
2015-07-27 03:41:48 -04:00
#define LRU_BITS 24
#define LRU_CLOCK_MAX ((1<<LRU_BITS)-1) /* Max value of obj->lru */
#define LRU_CLOCK_RESOLUTION 1000 /* LRU clock resolution in ms */
#define OBJ_SHARED_REFCOUNT INT_MAX
typedef struct redisObject {
unsigned type:4;
unsigned encoding:4;
unsigned lru:LRU_BITS; /* LRU time (relative to server.lruclock) or
* LFU data (least significant 8 bits frequency
* and most significant 16 bits decreas time). */
int refcount;
void *ptr;
} robj;
/* Macro used to obtain the current LRU clock.
* If the current resolution is lower than the frequency we refresh the
* LRU clock (as it should be in production servers) we return the
* precomputed value, otherwise we need to resort to a system call. */
2015-07-27 03:41:48 -04:00
#define LRU_CLOCK() ((1000/server.hz <= LRU_CLOCK_RESOLUTION) ? server.lruclock : getLRUClock())
2013-01-16 12:00:20 -05:00
/* Macro used to initialize a Redis object allocated on the stack.
* Note that this macro is taken near the structure definition to make sure
* we'll update it when the structure is changed, to avoid bugs like
* bug #85 introduced exactly in this way. */
#define initStaticStringObject(_var,_ptr) do { \
_var.refcount = 1; \
_var.type = OBJ_STRING; \
_var.encoding = OBJ_ENCODING_RAW; \
_var.ptr = _ptr; \
2016-04-25 09:49:57 -04:00
} while(0)
struct evictionPoolEntry; /* Defined in evict.c */
/* Redis database representation. There are multiple databases identified
* by integers from 0 (the default database) up to the max configured
* database. The database number is the 'id' field in the structure. */
typedef struct redisDb {
dict *dict; /* The keyspace for this DB */
dict *expires; /* Timeout of keys with a timeout set */
dict *blocking_keys; /* Keys with clients waiting for data (BLPOP)*/
A reimplementation of blocking operation internals. Redis provides support for blocking operations such as BLPOP or BRPOP. This operations are identical to normal LPOP and RPOP operations as long as there are elements in the target list, but if the list is empty they block waiting for new data to arrive to the list. All the clients blocked waiting for th same list are served in a FIFO way, so the first that blocked is the first to be served when there is more data pushed by another client into the list. The previous implementation of blocking operations was conceived to serve clients in the context of push operations. For for instance: 1) There is a client "A" blocked on list "foo". 2) The client "B" performs `LPUSH foo somevalue`. 3) The client "A" is served in the context of the "B" LPUSH, synchronously. Processing things in a synchronous way was useful as if "A" pushes a value that is served by "B", from the point of view of the database is a NOP (no operation) thing, that is, nothing is replicated, nothing is written in the AOF file, and so forth. However later we implemented two things: 1) Variadic LPUSH that could add multiple values to a list in the context of a single call. 2) BRPOPLPUSH that was a version of BRPOP that also provided a "PUSH" side effect when receiving data. This forced us to make the synchronous implementation more complex. If client "B" is waiting for data, and "A" pushes three elemnents in a single call, we needed to propagate an LPUSH with a missing argument in the AOF and replication link. We also needed to make sure to replicate the LPUSH side of BRPOPLPUSH, but only if in turn did not happened to serve another blocking client into another list ;) This were complex but with a few of mutually recursive functions everything worked as expected... until one day we introduced scripting in Redis. Scripting + synchronous blocking operations = Issue #614. Basically you can't "rewrite" a script to have just a partial effect on the replicas and AOF file if the script happened to serve a few blocked clients. The solution to all this problems, implemented by this commit, is to change the way we serve blocked clients. Instead of serving the blocked clients synchronously, in the context of the command performing the PUSH operation, it is now an asynchronous and iterative process: 1) If a key that has clients blocked waiting for data is the subject of a list push operation, We simply mark keys as "ready" and put it into a queue. 2) Every command pushing stuff on lists, as a variadic LPUSH, a script, or whatever it is, is replicated verbatim without any rewriting. 3) Every time a Redis command, a MULTI/EXEC block, or a script, completed its execution, we run the list of keys ready to serve blocked clients (as more data arrived), and process this list serving the blocked clients. 4) As a result of "3" maybe more keys are ready again for other clients (as a result of BRPOPLPUSH we may have push operations), so we iterate back to step "3" if it's needed. The new code has a much simpler semantics, and a simpler to understand implementation, with the disadvantage of not being able to "optmize out" a PUSH+BPOP as a No OP. This commit will be tested with care before the final merge, more tests will be added likely.
2012-09-04 04:37:49 -04:00
dict *ready_keys; /* Blocked keys that received a PUSH */
dict *watched_keys; /* WATCHED keys for MULTI/EXEC CAS */
int id; /* Database ID */
long long avg_ttl; /* Average TTL, just for stats */
} redisDb;
/* Client MULTI/EXEC state */
typedef struct multiCmd {
robj **argv;
int argc;
struct redisCommand *cmd;
} multiCmd;
typedef struct multiState {
multiCmd *commands; /* Array of MULTI commands */
int count; /* Total number of MULTI commands */
int minreplicas; /* MINREPLICAS for synchronous replication */
time_t minreplicas_timeout; /* MINREPLICAS timeout as unixtime. */
} multiState;
/* This structure holds the blocking operation state for a client.
* The fields used depend on client->btype. */
2010-11-08 17:38:01 -05:00
typedef struct blockingState {
/* Generic fields. */
mstime_t timeout; /* Blocking operation timeout. If UNIX current time
* is > timeout then the operation timed out. */
2015-07-27 03:41:48 -04:00
/* BLOCKED_LIST */
dict *keys; /* The keys we are waiting to terminate a blocking
2010-11-08 17:38:01 -05:00
* operation such as BLPOP. Otherwise NULL. */
robj *target; /* The key that should receive the element,
* for BRPOPLPUSH. */
2015-07-27 03:41:48 -04:00
/* BLOCKED_WAIT */
int numreplicas; /* Number of replicas we are waiting for ACK. */
long long reploffset; /* Replication offset to reach. */
2010-11-08 17:38:01 -05:00
} blockingState;
A reimplementation of blocking operation internals. Redis provides support for blocking operations such as BLPOP or BRPOP. This operations are identical to normal LPOP and RPOP operations as long as there are elements in the target list, but if the list is empty they block waiting for new data to arrive to the list. All the clients blocked waiting for th same list are served in a FIFO way, so the first that blocked is the first to be served when there is more data pushed by another client into the list. The previous implementation of blocking operations was conceived to serve clients in the context of push operations. For for instance: 1) There is a client "A" blocked on list "foo". 2) The client "B" performs `LPUSH foo somevalue`. 3) The client "A" is served in the context of the "B" LPUSH, synchronously. Processing things in a synchronous way was useful as if "A" pushes a value that is served by "B", from the point of view of the database is a NOP (no operation) thing, that is, nothing is replicated, nothing is written in the AOF file, and so forth. However later we implemented two things: 1) Variadic LPUSH that could add multiple values to a list in the context of a single call. 2) BRPOPLPUSH that was a version of BRPOP that also provided a "PUSH" side effect when receiving data. This forced us to make the synchronous implementation more complex. If client "B" is waiting for data, and "A" pushes three elemnents in a single call, we needed to propagate an LPUSH with a missing argument in the AOF and replication link. We also needed to make sure to replicate the LPUSH side of BRPOPLPUSH, but only if in turn did not happened to serve another blocking client into another list ;) This were complex but with a few of mutually recursive functions everything worked as expected... until one day we introduced scripting in Redis. Scripting + synchronous blocking operations = Issue #614. Basically you can't "rewrite" a script to have just a partial effect on the replicas and AOF file if the script happened to serve a few blocked clients. The solution to all this problems, implemented by this commit, is to change the way we serve blocked clients. Instead of serving the blocked clients synchronously, in the context of the command performing the PUSH operation, it is now an asynchronous and iterative process: 1) If a key that has clients blocked waiting for data is the subject of a list push operation, We simply mark keys as "ready" and put it into a queue. 2) Every command pushing stuff on lists, as a variadic LPUSH, a script, or whatever it is, is replicated verbatim without any rewriting. 3) Every time a Redis command, a MULTI/EXEC block, or a script, completed its execution, we run the list of keys ready to serve blocked clients (as more data arrived), and process this list serving the blocked clients. 4) As a result of "3" maybe more keys are ready again for other clients (as a result of BRPOPLPUSH we may have push operations), so we iterate back to step "3" if it's needed. The new code has a much simpler semantics, and a simpler to understand implementation, with the disadvantage of not being able to "optmize out" a PUSH+BPOP as a No OP. This commit will be tested with care before the final merge, more tests will be added likely.
2012-09-04 04:37:49 -04:00
/* The following structure represents a node in the server.ready_keys list,
* where we accumulate all the keys that had clients blocked with a blocking
* operation such as B[LR]POP, but received new data in the context of the
* last executed command.
*
* After the execution of every command or script, we run this list to check
* if as a result we should serve data to clients blocked, unblocking them.
* Note that server.ready_keys will not have duplicates as there dictionary
* also called ready_keys in every structure representing a Redis database,
* where we make sure to remember if a given key was already added in the
* server.ready_keys list. */
typedef struct readyList {
redisDb *db;
robj *key;
} readyList;
2013-01-16 12:00:20 -05:00
/* With multiplexing we need to take per-client state.
2013-11-20 01:14:27 -05:00
* Clients are taken in a linked list. */
typedef struct client {
uint64_t id; /* Client incremental unique ID. */
2015-08-06 03:41:11 -04:00
int fd; /* Client socket. */
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 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. */
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. */
2015-08-06 03:41:11 -04:00
time_t ctime; /* Client creation time. */
time_t lastinteraction; /* Time of the last interaction, used for timeout */
time_t obuf_soft_limit_reached_time;
2015-08-06 03:41:11 -04:00
int flags; /* Client flags: CLIENT_* macros. */
int authenticated; /* When requirepass is non-NULL. */
int replstate; /* Replication state if this is a slave. */
int repl_put_online_on_ack; /* Install slave write handler on ACK. */
2015-08-06 03:41:11 -04:00
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 reploff; /* Replication offset if this is our 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. */
2015-08-06 03:41:11 -04:00
char replrunid[CONFIG_RUN_ID_SIZE+1]; /* Master run id if is a master. */
int slave_listening_port; /* As configured with: REPLCONF 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 */
2015-07-27 03:41:48 -04:00
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. */
/* Response buffer */
int bufpos;
2015-07-27 03:41:48 -04:00
char buf[PROTO_REPLY_CHUNK_BYTES];
} client;
struct saveparam {
time_t seconds;
int changes;
};
struct moduleLoadQueueEntry {
sds path;
int argc;
robj **argv;
};
struct sharedObjectsStruct {
robj *crlf, *ok, *err, *emptybulk, *czero, *cone, *cnegone, *pong, *space,
*colon, *nullbulk, *nullmultibulk, *queued,
*emptymultibulk, *wrongtypeerr, *nokeyerr, *syntaxerr, *sameobjecterr,
*outofrangeerr, *noscripterr, *loadingerr, *slowscripterr, *bgsaveerr,
*masterdownerr, *roslaveerr, *execaborterr, *noautherr, *noreplicaserr,
*busykeyerr, *oomerr, *plus, *messagebulk, *pmessagebulk, *subscribebulk,
*unsubscribebulk, *psubscribebulk, *punsubscribebulk, *del, *unlink,
*rpop, *lpop, *lpush, *emptyscan,
2015-07-27 03:41:48 -04:00
*select[PROTO_SHARED_SELECT_CMDS],
*integers[OBJ_SHARED_INTEGERS],
*mbulkhdr[OBJ_SHARED_BULKHDR_LEN], /* "*<value>\r\n" */
*bulkhdr[OBJ_SHARED_BULKHDR_LEN]; /* "$<value>\r\n" */
sds minstring, maxstring;
};
/* ZSETs use a specialized version of Skiplists */
typedef struct zskiplistNode {
sds ele;
double score;
struct zskiplistNode *backward;
struct zskiplistLevel {
struct zskiplistNode *forward;
unsigned int span;
} level[];
} zskiplistNode;
typedef struct zskiplist {
struct zskiplistNode *header, *tail;
unsigned long length;
int level;
} zskiplist;
typedef struct zset {
dict *dict;
zskiplist *zsl;
} zset;
typedef struct clientBufferLimitsConfig {
unsigned long long hard_limit_bytes;
unsigned long long soft_limit_bytes;
time_t soft_limit_seconds;
} clientBufferLimitsConfig;
2015-07-28 10:58:04 -04:00
extern clientBufferLimitsConfig clientBufferLimitsDefaults[CLIENT_TYPE_OBUF_COUNT];
/* The redisOp structure defines a Redis Operation, that is an instance of
* a command with an argument vector, database ID, propagation target
2015-07-27 03:41:48 -04:00
* (PROPAGATE_*), and command pointer.
*
* Currently only used to additionally propagate more commands to AOF/Replication
* after the propagation of the executed command. */
typedef struct redisOp {
robj **argv;
int argc, dbid, target;
struct redisCommand *cmd;
} redisOp;
/* Defines an array of Redis operations. There is an API to add to this
* structure in a easy way.
*
* redisOpArrayInit();
* redisOpArrayAppend();
* redisOpArrayFree();
*/
typedef struct redisOpArray {
redisOp *ops;
int numops;
} redisOpArray;
2011-03-29 11:51:15 -04:00
/*-----------------------------------------------------------------------------
* Global server state
*----------------------------------------------------------------------------*/
struct clusterState;
2014-08-07 06:14:21 -04:00
/* AIX defines hz to __hz, we don't use this define and in order to allow
* Redis build on AIX we need to undef it. */
#ifdef _AIX
#undef hz
#endif
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 hz; /* serverCron() calls frequency in hertz */
redisDb *db;
dict *commands; /* Command table */
dict *orig_commands; /* Command table before command renaming. */
aeEventLoop *el;
2015-07-27 03:41:48 -04:00
unsigned lruclock:LRU_BITS; /* Clock for LRU eviction */
int shutdown_asap; /* SHUTDOWN needed ASAP */
int activerehashing; /* Incremental rehash in serverCron() */
char *requirepass; /* Pass for AUTH command, or NULL */
char *pidfile; /* PID file path */
int arch_bits; /* 32 or 64 depending on sizeof(long) */
int cronloops; /* Number of times the cron function run */
2015-07-27 03:41:48 -04:00
char runid[CONFIG_RUN_ID_SIZE+1]; /* ID always different at every exec. */
int sentinel_mode; /* True if this instance is a Sentinel. */
2016-03-06 07:44:24 -05:00
/* Modules */
dict *moduleapi; /* Exported APIs dictionary for modules. */
list *loadmodule_queue; /* List of modules to load at startup. */
/* Networking */
int port; /* TCP listening port */
int tcp_backlog; /* TCP listen() backlog */
2015-07-27 03:41:48 -04:00
char *bindaddr[CONFIG_BINDADDR_MAX]; /* Addresses we should bind to */
2013-07-04 12:50:15 -04:00
int bindaddr_count; /* Number of addresses in server.bindaddr[] */
char *unixsocket; /* UNIX socket path */
mode_t unixsocketperm; /* UNIX socket permission */
2015-07-27 03:41:48 -04:00
int ipfd[CONFIG_BINDADDR_MAX]; /* TCP socket file descriptors */
int ipfd_count; /* Used slots in ipfd[] */
int sofd; /* Unix socket file descriptor */
2015-07-27 03:41:48 -04:00
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 *slaves, *monitors; /* List of slaves and MONITORs */
client *current_client; /* Current client, only used on crash report */
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 */
uint64_t next_client_id; /* Next client unique ID. Incremental. */
int protected_mode; /* Don't accept external connections. */
/* 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 */
A reimplementation of blocking operation internals. Redis provides support for blocking operations such as BLPOP or BRPOP. This operations are identical to normal LPOP and RPOP operations as long as there are elements in the target list, but if the list is empty they block waiting for new data to arrive to the list. All the clients blocked waiting for th same list are served in a FIFO way, so the first that blocked is the first to be served when there is more data pushed by another client into the list. The previous implementation of blocking operations was conceived to serve clients in the context of push operations. For for instance: 1) There is a client "A" blocked on list "foo". 2) The client "B" performs `LPUSH foo somevalue`. 3) The client "A" is served in the context of the "B" LPUSH, synchronously. Processing things in a synchronous way was useful as if "A" pushes a value that is served by "B", from the point of view of the database is a NOP (no operation) thing, that is, nothing is replicated, nothing is written in the AOF file, and so forth. However later we implemented two things: 1) Variadic LPUSH that could add multiple values to a list in the context of a single call. 2) BRPOPLPUSH that was a version of BRPOP that also provided a "PUSH" side effect when receiving data. This forced us to make the synchronous implementation more complex. If client "B" is waiting for data, and "A" pushes three elemnents in a single call, we needed to propagate an LPUSH with a missing argument in the AOF and replication link. We also needed to make sure to replicate the LPUSH side of BRPOPLPUSH, but only if in turn did not happened to serve another blocking client into another list ;) This were complex but with a few of mutually recursive functions everything worked as expected... until one day we introduced scripting in Redis. Scripting + synchronous blocking operations = Issue #614. Basically you can't "rewrite" a script to have just a partial effect on the replicas and AOF file if the script happened to serve a few blocked clients. The solution to all this problems, implemented by this commit, is to change the way we serve blocked clients. Instead of serving the blocked clients synchronously, in the context of the command performing the PUSH operation, it is now an asynchronous and iterative process: 1) If a key that has clients blocked waiting for data is the subject of a list push operation, We simply mark keys as "ready" and put it into a queue. 2) Every command pushing stuff on lists, as a variadic LPUSH, a script, or whatever it is, is replicated verbatim without any rewriting. 3) Every time a Redis command, a MULTI/EXEC block, or a script, completed its execution, we run the list of keys ready to serve blocked clients (as more data arrived), and process this list serving the blocked clients. 4) As a result of "3" maybe more keys are ready again for other clients (as a result of BRPOPLPUSH we may have push operations), so we iterate back to step "3" if it's needed. The new code has a much simpler semantics, and a simpler to understand implementation, with the disadvantage of not being able to "optmize out" a PUSH+BPOP as a No OP. This commit will be tested with care before the final merge, more tests will be added likely.
2012-09-04 04:37:49 -04:00
struct redisCommand *delCommand, *multiCommand, *lpushCommand, *lpopCommand,
*rpopCommand, *sremCommand, *execCommand;
/* 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 */
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 */
size_t stat_peak_memory; /* Max used memory record */
2013-01-16 12:00:20 -05:00
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 */
size_t resident_set_size; /* RSS sampled in serverCron(). */
long long stat_net_input_bytes; /* Bytes read from network. */
long long stat_net_output_bytes; /* Bytes written to network. */
/* 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 */
2015-07-27 03:41:48 -04:00
long long samples[STATS_METRIC_SAMPLES];
int idx;
2015-07-27 03:41:48 -04:00
} 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. */
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. */
2015-07-27 03:41:48 -04:00
int supervised_mode; /* See SUPERVISED_* */
int daemonize; /* True if running as a daemon */
2015-07-28 10:58:04 -04:00
clientBufferLimitsConfig client_obuf_limits[CLIENT_TYPE_OBUF_COUNT];
/* AOF persistence */
2015-07-27 03:41:48 -04:00
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. */
int aof_rewrite_scheduled; /* Rewrite once BGSAVE terminates. */
2011-12-21 06:17:02 -05:00
pid_t aof_child_pid; /* PID if rewriting process */
Allow an AOF rewrite buffer > 2GB (Fix for issue #504). During the AOF rewrite process, the parent process needs to accumulate the new writes in an in-memory buffer: when the child will terminate the AOF rewriting process this buffer (that ist the difference between the dataset when the rewrite was started, and the current dataset) is flushed to the new AOF file. We used to implement this buffer using an sds.c string, but sds.c has a 2GB limit. Sometimes the dataset can be big enough, the amount of writes so high, and the rewrite process slow enough that we overflow the 2GB limit, causing a crash, documented on github by issue #504. In order to prevent this from happening, this commit introduces a new system to accumulate writes, implemented by a linked list of blocks of 10 MB each, so that we also avoid paying the reallocation cost. Note that theoretically modern operating systems may implement realloc() simply as a remaping of the old pages, thus with very good performances, see for instance the mremap() syscall on Linux. However this is not always true, and jemalloc by default avoids doing this because there are issues with the current implementation of mremap(). For this reason we are using a linked list of blocks instead of a single block that gets reallocated again and again. The changes in this commit lacks testing, that will be performed before merging into the unstable branch. This fix will not enter 2.4 because it is too invasive. However 2.4 will log a warning when the AOF rewrite buffer is near to the 2GB limit.
2012-05-22 07:03:41 -04:00
list *aof_rewrite_buf_blocks; /* Hold changes during an AOF rewrite. */
2011-12-21 06:17:02 -05:00
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 */
2011-12-21 06:17:02 -05:00
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 rewriting? */
int aof_last_write_status; /* C_OK or C_ERR */
int aof_last_write_errno; /* Valid if aof_last_write_status is ERR */
2014-09-05 05:48:35 -04:00
int aof_load_truncated; /* Don't stop on unexpected AOF EOF. */
/* 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 */
2011-12-21 06:22:13 -05:00
pid_t rdb_child_pid; /* PID of RDB saving child */
struct saveparam *saveparams; /* Save points array for RDB */
int saveparamslen; /* Number of saving points */
2011-12-21 06:22:13 -05:00
char *rdb_filename; /* Name of RDB file */
int rdb_compression; /* Use compression in RDB? */
int rdb_checksum; /* Use RDB checksum? */
2013-01-16 12:00:20 -05:00
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_result_to_parent; /* RDB pipes used to return the state */
int rdb_pipe_read_result_from_child; /* of each slave in diskless SYNC. */
/* 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) */
int slaveseldb; /* Last SELECTed DB in replication output */
long long master_repl_offset; /* Global replication offset */
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 */
long long repl_backlog_off; /* Replication offset of first byte in the
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; /* Send RDB to slaves sockets directly. */
int repl_diskless_sync_delay; /* Delay to start a diskless repl BGSAVE. */
/* Replication (slave) */
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 */
2011-12-21 06:23:18 -05:00
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. */
int repl_transfer_s; /* Slave -> Master SYNC socket */
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? */
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. */
char repl_master_runid[CONFIG_RUN_ID_SIZE+1]; /* Master run id for PSYNC.*/
long long repl_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 */
2013-01-16 12:00:20 -05:00
int maxmemory_policy; /* Policy for key eviction */
int maxmemory_samples; /* Pricision of random sampling */
unsigned int lfu_log_factor; /* LFU logarithmic counter factor. */
unsigned int lfu_decay_time; /* LFU counter decay factor. */
/* Blocked clients */
unsigned int bpop_blocked_clients; /* Number of clients blocked by lists */
list *unblocked_clients; /* list of clients to unblock before next loop */
A reimplementation of blocking operation internals. Redis provides support for blocking operations such as BLPOP or BRPOP. This operations are identical to normal LPOP and RPOP operations as long as there are elements in the target list, but if the list is empty they block waiting for new data to arrive to the list. All the clients blocked waiting for th same list are served in a FIFO way, so the first that blocked is the first to be served when there is more data pushed by another client into the list. The previous implementation of blocking operations was conceived to serve clients in the context of push operations. For for instance: 1) There is a client "A" blocked on list "foo". 2) The client "B" performs `LPUSH foo somevalue`. 3) The client "A" is served in the context of the "B" LPUSH, synchronously. Processing things in a synchronous way was useful as if "A" pushes a value that is served by "B", from the point of view of the database is a NOP (no operation) thing, that is, nothing is replicated, nothing is written in the AOF file, and so forth. However later we implemented two things: 1) Variadic LPUSH that could add multiple values to a list in the context of a single call. 2) BRPOPLPUSH that was a version of BRPOP that also provided a "PUSH" side effect when receiving data. This forced us to make the synchronous implementation more complex. If client "B" is waiting for data, and "A" pushes three elemnents in a single call, we needed to propagate an LPUSH with a missing argument in the AOF and replication link. We also needed to make sure to replicate the LPUSH side of BRPOPLPUSH, but only if in turn did not happened to serve another blocking client into another list ;) This were complex but with a few of mutually recursive functions everything worked as expected... until one day we introduced scripting in Redis. Scripting + synchronous blocking operations = Issue #614. Basically you can't "rewrite" a script to have just a partial effect on the replicas and AOF file if the script happened to serve a few blocked clients. The solution to all this problems, implemented by this commit, is to change the way we serve blocked clients. Instead of serving the blocked clients synchronously, in the context of the command performing the PUSH operation, it is now an asynchronous and iterative process: 1) If a key that has clients blocked waiting for data is the subject of a list push operation, We simply mark keys as "ready" and put it into a queue. 2) Every command pushing stuff on lists, as a variadic LPUSH, a script, or whatever it is, is replicated verbatim without any rewriting. 3) Every time a Redis command, a MULTI/EXEC block, or a script, completed its execution, we run the list of keys ready to serve blocked clients (as more data arrived), and process this list serving the blocked clients. 4) As a result of "3" maybe more keys are ready again for other clients (as a result of BRPOPLPUSH we may have push operations), so we iterate back to step "3" if it's needed. The new code has a much simpler semantics, and a simpler to understand implementation, with the disadvantage of not being able to "optmize out" a PUSH+BPOP as a No OP. This commit will be tested with care before the final merge, more tests will be added likely.
2012-09-04 04:37:49 -04:00
list *ready_keys; /* List of readyList structures for BLPOP & co */
/* 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 */
2012-01-03 01:14:10 -05:00
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;
/* List parameters */
int list_max_ziplist_size;
int list_compress_depth;
/* time cache */
time_t unixtime; /* Unix time sampled every cron cycle. */
long long mstime; /* Like 'unixtime' but with milliseconds resolution. */
/* 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
2015-07-27 03:41:48 -04:00
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
2015-10-29 08:50:04 -04:00
there is at least an uncovered slot.*/
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. */
/* 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 */
dict *lua_scripts; /* A dictionary of SHA1 -> Lua scripts */
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. */
2015-10-29 08:50:04 -04:00
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;
2013-01-16 12:00:20 -05:00
/* Assert & bug reporting */
const char *assert_failed;
const char *assert_file;
2011-11-24 09:47:26 -05:00
int assert_line;
int bug_report_start; /* True if bug report header was already logged. */
2012-03-27 05:47:51 -04:00
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 */
};
typedef struct pubsubPattern {
client *client;
robj *pattern;
} pubsubPattern;
typedef void redisCommandProc(client *c);
typedef int *redisGetKeysProc(struct redisCommand *cmd, robj **argv, int argc, int *numkeys);
struct redisCommand {
char *name;
redisCommandProc *proc;
int arity;
2013-01-16 12:00:20 -05:00
char *sflags; /* Flags as string representation, one char per flag. */
int flags; /* The actual flags, obtained from the 'sflags' field. */
/* Use a function to determine keys arguments in a command line.
2011-06-25 06:22:03 -04:00
* Used for Redis Cluster redirect. */
redisGetKeysProc *getkeys_proc;
/* What keys should be loaded in background when calling this command? */
int firstkey; /* The first argument that's a key (0 = no keys) */
2013-01-16 12:00:20 -05:00
int lastkey; /* The last argument that's a key */
int keystep; /* The step between first and last key */
long long microseconds, calls;
};
struct redisFunctionSym {
char *name;
unsigned long pointer;
};
typedef struct _redisSortObject {
robj *obj;
union {
double score;
robj *cmpobj;
} u;
} redisSortObject;
typedef struct _redisSortOperation {
int type;
robj *pattern;
} redisSortOperation;
/* Structure to hold list iteration abstraction. */
typedef struct {
robj *subject;
unsigned char encoding;
unsigned char direction; /* Iteration direction */
quicklistIter *iter;
} listTypeIterator;
/* Structure for an entry while iterating over a list. */
typedef struct {
listTypeIterator *li;
quicklistEntry entry; /* Entry in quicklist */
} listTypeEntry;
/* Structure to hold set iteration abstraction. */
typedef struct {
robj *subject;
int encoding;
int ii; /* intset iterator */
dictIterator *di;
} setTypeIterator;
2013-01-16 12:00:20 -05:00
/* Structure to hold hash iteration abstraction. Note that iteration over
* hashes involves both fields and values. Because it is possible that
* not both are required, store pointers in the iterator to avoid
* unnecessary memory allocation for fields/values. */
typedef struct {
2012-01-03 01:14:10 -05:00
robj *subject;
int encoding;
2012-01-03 01:14:10 -05:00
unsigned char *fptr, *vptr;
dictIterator *di;
dictEntry *de;
} hashTypeIterator;
#define OBJ_HASH_KEY 1
#define OBJ_HASH_VALUE 2
/*-----------------------------------------------------------------------------
* Extern declarations
*----------------------------------------------------------------------------*/
extern struct redisServer server;
extern struct sharedObjectsStruct shared;
extern dictType objectKeyPointerValueDictType;
extern dictType setDictType;
extern dictType zsetDictType;
2011-03-29 11:51:15 -04:00
extern dictType clusterNodesDictType;
extern dictType clusterNodesBlackListDictType;
extern dictType dbDictType;
extern dictType shaScriptObjectDictType;
extern double R_Zero, R_PosInf, R_NegInf, R_Nan;
2012-03-27 12:18:57 -04:00
extern dictType hashDictType;
extern dictType replScriptCacheDictType;
extern dictType keyptrDictType;
2016-03-06 07:44:24 -05:00
extern dictType modulesDictType;
/*-----------------------------------------------------------------------------
* Functions prototypes
*----------------------------------------------------------------------------*/
2016-03-06 07:44:24 -05:00
/* Modules */
void moduleInitModulesSystem(void);
int moduleLoad(const char *path, void **argv, int argc);
2016-03-06 07:44:24 -05:00
void moduleLoadFromQueue(void);
int *moduleGetCommandKeysViaAPI(struct redisCommand *cmd, robj **argv, int argc, int *numkeys);
moduleType *moduleTypeLookupModuleByID(uint64_t id);
void moduleTypeNameByID(char *name, uint64_t moduleid);
2016-03-06 07:44:24 -05:00
/* Utils */
long long ustime(void);
long long mstime(void);
void getRandomHexChars(char *p, unsigned int len);
uint64_t crc64(uint64_t crc, const unsigned char *s, uint64_t l);
void exitFromChild(int retcode);
size_t redisPopcount(void *s, long count);
void redisSetProcTitle(char *title);
/* networking.c -- Networking and Client related operations */
client *createClient(int fd);
void closeTimedoutClients(void);
void freeClient(client *c);
void freeClientAsync(client *c);
void resetClient(client *c);
void sendReplyToClient(aeEventLoop *el, int fd, void *privdata, int mask);
void *addDeferredMultiBulkLength(client *c);
void setDeferredMultiBulkLength(client *c, void *node, long length);
void processInputBuffer(client *c);
void acceptHandler(aeEventLoop *el, int fd, void *privdata, int mask);
void acceptTcpHandler(aeEventLoop *el, int fd, void *privdata, int mask);
void acceptUnixHandler(aeEventLoop *el, int fd, void *privdata, int mask);
void readQueryFromClient(aeEventLoop *el, int fd, void *privdata, int mask);
void addReplyBulk(client *c, robj *obj);
void addReplyBulkCString(client *c, const char *s);
void addReplyBulkCBuffer(client *c, const void *p, size_t len);
void addReplyBulkLongLong(client *c, long long ll);
void addReply(client *c, robj *obj);
void addReplySds(client *c, sds s);
void addReplyBulkSds(client *c, sds s);
void addReplyError(client *c, const char *err);
void addReplyStatus(client *c, const char *status);
void addReplyDouble(client *c, double d);
void addReplyHumanLongDouble(client *c, long double d);
void addReplyLongLong(client *c, long long ll);
void addReplyMultiBulkLen(client *c, long length);
void copyClientOutputBuffer(client *dst, client *src);
void *dupClientReplyValue(void *o);
void getClientsMaxBuffers(unsigned long *longest_output_list,
unsigned long *biggest_input_buffer);
char *getClientPeerId(client *client);
sds catClientInfoString(sds s, client *client);
sds getAllClientsInfoString(void);
void rewriteClientCommandVector(client *c, int argc, ...);
void rewriteClientCommandArgument(client *c, int i, robj *newval);
void replaceClientCommandVector(client *c, int argc, robj **argv);
unsigned long getClientOutputBufferMemoryUsage(client *c);
void freeClientsInAsyncFreeQueue(void);
void asyncCloseClientOnOutputBufferLimitReached(client *c);
int getClientType(client *c);
int getClientTypeByName(char *name);
char *getClientTypeName(int class);
2012-02-06 10:56:42 -05:00
void flushSlavesOutputBuffers(void);
void disconnectSlaves(void);
int listenToPort(int port, int *fds, int *count);
void pauseClients(mstime_t duration);
int clientsArePaused(void);
int processEventsWhileBlocked(void);
int handleClientsWithPendingWrites(void);
int clientHasPendingReplies(client *c);
void unlinkClient(client *c);
2015-11-06 10:19:59 -05:00
int writeToClient(int fd, client *c, int handler_installed);
#ifdef __GNUC__
void addReplyErrorFormat(client *c, const char *fmt, ...)
__attribute__((format(printf, 2, 3)));
void addReplyStatusFormat(client *c, const char *fmt, ...)
__attribute__((format(printf, 2, 3)));
#else
void addReplyErrorFormat(client *c, const char *fmt, ...);
void addReplyStatusFormat(client *c, const char *fmt, ...);
#endif
/* List data type */
void listTypeTryConversion(robj *subject, robj *value);
void listTypePush(robj *subject, robj *value, int where);
robj *listTypePop(robj *subject, int where);
unsigned long listTypeLength(const robj *subject);
listTypeIterator *listTypeInitIterator(robj *subject, long index, unsigned char direction);
void listTypeReleaseIterator(listTypeIterator *li);
int listTypeNext(listTypeIterator *li, listTypeEntry *entry);
robj *listTypeGet(listTypeEntry *entry);
void listTypeInsert(listTypeEntry *entry, robj *value, int where);
int listTypeEqual(listTypeEntry *entry, robj *o);
void listTypeDelete(listTypeIterator *iter, listTypeEntry *entry);
void listTypeConvert(robj *subject, int enc);
void unblockClientWaitingData(client *c);
A reimplementation of blocking operation internals. Redis provides support for blocking operations such as BLPOP or BRPOP. This operations are identical to normal LPOP and RPOP operations as long as there are elements in the target list, but if the list is empty they block waiting for new data to arrive to the list. All the clients blocked waiting for th same list are served in a FIFO way, so the first that blocked is the first to be served when there is more data pushed by another client into the list. The previous implementation of blocking operations was conceived to serve clients in the context of push operations. For for instance: 1) There is a client "A" blocked on list "foo". 2) The client "B" performs `LPUSH foo somevalue`. 3) The client "A" is served in the context of the "B" LPUSH, synchronously. Processing things in a synchronous way was useful as if "A" pushes a value that is served by "B", from the point of view of the database is a NOP (no operation) thing, that is, nothing is replicated, nothing is written in the AOF file, and so forth. However later we implemented two things: 1) Variadic LPUSH that could add multiple values to a list in the context of a single call. 2) BRPOPLPUSH that was a version of BRPOP that also provided a "PUSH" side effect when receiving data. This forced us to make the synchronous implementation more complex. If client "B" is waiting for data, and "A" pushes three elemnents in a single call, we needed to propagate an LPUSH with a missing argument in the AOF and replication link. We also needed to make sure to replicate the LPUSH side of BRPOPLPUSH, but only if in turn did not happened to serve another blocking client into another list ;) This were complex but with a few of mutually recursive functions everything worked as expected... until one day we introduced scripting in Redis. Scripting + synchronous blocking operations = Issue #614. Basically you can't "rewrite" a script to have just a partial effect on the replicas and AOF file if the script happened to serve a few blocked clients. The solution to all this problems, implemented by this commit, is to change the way we serve blocked clients. Instead of serving the blocked clients synchronously, in the context of the command performing the PUSH operation, it is now an asynchronous and iterative process: 1) If a key that has clients blocked waiting for data is the subject of a list push operation, We simply mark keys as "ready" and put it into a queue. 2) Every command pushing stuff on lists, as a variadic LPUSH, a script, or whatever it is, is replicated verbatim without any rewriting. 3) Every time a Redis command, a MULTI/EXEC block, or a script, completed its execution, we run the list of keys ready to serve blocked clients (as more data arrived), and process this list serving the blocked clients. 4) As a result of "3" maybe more keys are ready again for other clients (as a result of BRPOPLPUSH we may have push operations), so we iterate back to step "3" if it's needed. The new code has a much simpler semantics, and a simpler to understand implementation, with the disadvantage of not being able to "optmize out" a PUSH+BPOP as a No OP. This commit will be tested with care before the final merge, more tests will be added likely.
2012-09-04 04:37:49 -04:00
void handleClientsBlockedOnLists(void);
void popGenericCommand(client *c, int where);
void signalListAsReady(redisDb *db, robj *key);
/* MULTI/EXEC/WATCH... */
void unwatchAllKeys(client *c);
void initClientMultiState(client *c);
void freeClientMultiState(client *c);
void queueMultiCommand(client *c);
void touchWatchedKey(redisDb *db, robj *key);
void touchWatchedKeysOnFlush(int dbid);
void discardTransaction(client *c);
void flagTransaction(client *c);
void execCommandPropagateMulti(client *c);
/* Redis object implementation */
void decrRefCount(robj *o);
void decrRefCountVoid(void *o);
void incrRefCount(robj *o);
robj *makeObjectShared(robj *o);
robj *resetRefCount(robj *obj);
void freeStringObject(robj *o);
void freeListObject(robj *o);
void freeSetObject(robj *o);
void freeZsetObject(robj *o);
void freeHashObject(robj *o);
robj *createObject(int type, void *ptr);
robj *createStringObject(const char *ptr, size_t len);
robj *createRawStringObject(const char *ptr, size_t len);
robj *createEmbeddedStringObject(const char *ptr, size_t len);
robj *dupStringObject(const robj *o);
int isSdsRepresentableAsLongLong(sds s, long long *llval);
int isObjectRepresentableAsLongLong(robj *o, long long *llongval);
robj *tryObjectEncoding(robj *o);
robj *getDecodedObject(robj *o);
size_t stringObjectLen(robj *o);
robj *createStringObjectFromLongLong(long long value);
robj *createStringObjectFromLongDouble(long double value, int humanfriendly);
robj *createQuicklistObject(void);
robj *createZiplistObject(void);
robj *createSetObject(void);
robj *createIntsetObject(void);
robj *createHashObject(void);
robj *createZsetObject(void);
robj *createZsetZiplistObject(void);
robj *createModuleObject(moduleType *mt, void *value);
int getLongFromObjectOrReply(client *c, robj *o, long *target, const char *msg);
int checkType(client *c, robj *o, int type);
int getLongLongFromObjectOrReply(client *c, robj *o, long long *target, const char *msg);
int getDoubleFromObjectOrReply(client *c, robj *o, double *target, const char *msg);
int getDoubleFromObject(const robj *o, double *target);
int getLongLongFromObject(robj *o, long long *target);
2011-11-12 13:27:35 -05:00
int getLongDoubleFromObject(robj *o, long double *target);
int getLongDoubleFromObjectOrReply(client *c, robj *o, long double *target, const char *msg);
char *strEncoding(int encoding);
int compareStringObjects(robj *a, robj *b);
int collateStringObjects(robj *a, robj *b);
int equalStringObjects(robj *a, robj *b);
unsigned long long estimateObjectIdleTime(robj *o);
#define sdsEncodedObject(objptr) (objptr->encoding == OBJ_ENCODING_RAW || objptr->encoding == OBJ_ENCODING_EMBSTR)
/* Synchronous I/O with timeout */
ssize_t syncWrite(int fd, char *ptr, ssize_t size, long long timeout);
ssize_t syncRead(int fd, char *ptr, ssize_t size, long long timeout);
ssize_t syncReadLine(int fd, char *ptr, ssize_t size, long long timeout);
/* Replication */
void replicationFeedSlaves(list *slaves, int dictid, robj **argv, int argc);
void replicationFeedMonitors(client *c, list *monitors, int dictid, robj **argv, int argc);
void updateSlavesWaitingBgsave(int bgsaveerr, int type);
void replicationCron(void);
void replicationHandleMasterDisconnection(void);
void replicationCacheMaster(client *c);
void resizeReplicationBacklog(long long newsize);
void replicationSetMaster(char *ip, int port);
void replicationUnsetMaster(void);
void refreshGoodSlavesCount(void);
void replicationScriptCacheInit(void);
void replicationScriptCacheFlush(void);
void replicationScriptCacheAdd(sds sha1);
int replicationScriptCacheExists(sds sha1);
void processClientsWaitingReplicas(void);
void unblockClientWaitingReplicas(client *c);
int replicationCountAcksByOffset(long long offset);
void replicationSendNewlineToMaster(void);
long long replicationGetSlaveOffset(void);
char *replicationGetSlaveName(client *c);
long long getPsyncInitialOffset(void);
int replicationSetupSlaveForFullResync(client *slave, long long offset);
/* Generic persistence functions */
void startLoading(FILE *fp);
void loadingProgress(off_t pos);
void stopLoading(void);
/* RDB persistence */
#include "rdb.h"
2016-08-09 05:07:32 -04:00
int rdbSaveRio(rio *rdb, int *error, int flags);
/* AOF persistence */
void flushAppendOnlyFile(int force);
void feedAppendOnlyFile(struct redisCommand *cmd, int dictid, robj **argv, int argc);
void aofRemoveTempFile(pid_t childpid);
int rewriteAppendOnlyFileBackground(void);
int loadAppendOnlyFile(char *filename);
void stopAppendOnly(void);
int startAppendOnly(void);
void backgroundRewriteDoneHandler(int exitcode, int bysignal);
Allow an AOF rewrite buffer > 2GB (Fix for issue #504). During the AOF rewrite process, the parent process needs to accumulate the new writes in an in-memory buffer: when the child will terminate the AOF rewriting process this buffer (that ist the difference between the dataset when the rewrite was started, and the current dataset) is flushed to the new AOF file. We used to implement this buffer using an sds.c string, but sds.c has a 2GB limit. Sometimes the dataset can be big enough, the amount of writes so high, and the rewrite process slow enough that we overflow the 2GB limit, causing a crash, documented on github by issue #504. In order to prevent this from happening, this commit introduces a new system to accumulate writes, implemented by a linked list of blocks of 10 MB each, so that we also avoid paying the reallocation cost. Note that theoretically modern operating systems may implement realloc() simply as a remaping of the old pages, thus with very good performances, see for instance the mremap() syscall on Linux. However this is not always true, and jemalloc by default avoids doing this because there are issues with the current implementation of mremap(). For this reason we are using a linked list of blocks instead of a single block that gets reallocated again and again. The changes in this commit lacks testing, that will be performed before merging into the unstable branch. This fix will not enter 2.4 because it is too invasive. However 2.4 will log a warning when the AOF rewrite buffer is near to the 2GB limit.
2012-05-22 07:03:41 -04:00
void aofRewriteBufferReset(void);
unsigned long aofRewriteBufferSize(void);
/* Sorted sets data type */
2016-04-14 09:58:49 -04:00
/* Input flags. */
#define ZADD_NONE 0
#define ZADD_INCR (1<<0) /* Increment the score instead of setting it. */
#define ZADD_NX (1<<1) /* Don't touch elements not already existing. */
#define ZADD_XX (1<<2) /* Only touch elements already exisitng. */
/* Output flags. */
#define ZADD_NOP (1<<3) /* Operation not performed because of conditionals.*/
#define ZADD_NAN (1<<4) /* Only touch elements already exisitng. */
#define ZADD_ADDED (1<<5) /* The element was new and was added. */
#define ZADD_UPDATED (1<<6) /* The element already existed, score updated. */
/* Flags only used by the ZADD command but not by zsetAdd() API: */
#define ZADD_CH (1<<16) /* Return num of elements added or updated. */
/* Struct to hold a inclusive/exclusive range spec by score comparison. */
typedef struct {
double min, max;
int minex, maxex; /* are min or max exclusive? */
} zrangespec;
/* Struct to hold an inclusive/exclusive range spec by lexicographic comparison. */
typedef struct {
sds min, max; /* May be set to shared.(minstring|maxstring) */
int minex, maxex; /* are min or max exclusive? */
} zlexrangespec;
zskiplist *zslCreate(void);
void zslFree(zskiplist *zsl);
zskiplistNode *zslInsert(zskiplist *zsl, double score, sds ele);
unsigned char *zzlInsert(unsigned char *zl, sds ele, double score);
int zslDelete(zskiplist *zsl, double score, sds ele, zskiplistNode **node);
zskiplistNode *zslFirstInRange(zskiplist *zsl, zrangespec *range);
zskiplistNode *zslLastInRange(zskiplist *zsl, zrangespec *range);
2011-03-14 08:30:06 -04:00
double zzlGetScore(unsigned char *sptr);
void zzlNext(unsigned char *zl, unsigned char **eptr, unsigned char **sptr);
void zzlPrev(unsigned char *zl, unsigned char **eptr, unsigned char **sptr);
2016-04-19 09:22:33 -04:00
unsigned char *zzlFirstInRange(unsigned char *zl, zrangespec *range);
2016-04-20 06:38:14 -04:00
unsigned char *zzlLastInRange(unsigned char *zl, zrangespec *range);
unsigned int zsetLength(const robj *zobj);
void zsetConvert(robj *zobj, int encoding);
void zsetConvertToZiplistIfNeeded(robj *zobj, size_t maxelelen);
int zsetScore(robj *zobj, sds member, double *score);
unsigned long zslGetRank(zskiplist *zsl, double score, sds o);
2016-04-14 09:58:49 -04:00
int zsetAdd(robj *zobj, double score, sds ele, int *flags, double *newscore);
2016-04-15 06:46:18 -04:00
long zsetRank(robj *zobj, sds ele, int reverse);
2016-04-15 09:20:25 -04:00
int zsetDel(robj *zobj, sds ele);
2016-04-19 09:22:33 -04:00
sds ziplistGetObject(unsigned char *sptr);
2016-04-19 11:02:24 -04:00
int zslValueGteMin(double value, zrangespec *spec);
int zslValueLteMax(double value, zrangespec *spec);
2016-04-20 17:01:40 -04:00
void zslFreeLexRange(zlexrangespec *spec);
2016-04-21 03:27:13 -04:00
int zslParseLexRange(robj *min, robj *max, zlexrangespec *spec);
unsigned char *zzlFirstInLexRange(unsigned char *zl, zlexrangespec *range);
unsigned char *zzlLastInLexRange(unsigned char *zl, zlexrangespec *range);
zskiplistNode *zslFirstInLexRange(zskiplist *zsl, zlexrangespec *range);
zskiplistNode *zslLastInLexRange(zskiplist *zsl, zlexrangespec *range);
2016-04-21 05:17:00 -04:00
int zzlLexValueGteMin(unsigned char *p, zlexrangespec *spec);
int zzlLexValueLteMax(unsigned char *p, zlexrangespec *spec);
int zslLexValueGteMin(sds value, zlexrangespec *spec);
int zslLexValueLteMax(sds value, zlexrangespec *spec);
/* Core functions */
int freeMemoryIfNeeded(void);
int processCommand(client *c);
2011-03-06 11:49:22 -05:00
void setupSignalHandlers(void);
struct redisCommand *lookupCommand(sds name);
struct redisCommand *lookupCommandByCString(char *s);
struct redisCommand *lookupCommandOrOriginal(sds name);
void call(client *c, int flags);
2012-02-28 10:20:41 -05:00
void propagate(struct redisCommand *cmd, int dbid, robj **argv, int argc, int flags);
void alsoPropagate(struct redisCommand *cmd, int dbid, robj **argv, int argc, int target);
void forceCommandPropagation(client *c, int flags);
void preventCommandPropagation(client *c);
void preventCommandAOF(client *c);
void preventCommandReplication(client *c);
int prepareForShutdown();
#ifdef __GNUC__
2015-07-26 09:17:43 -04:00
void serverLog(int level, const char *fmt, ...)
__attribute__((format(printf, 2, 3)));
#else
2015-07-26 09:17:43 -04:00
void serverLog(int level, const char *fmt, ...);
#endif
2015-07-26 09:17:43 -04:00
void serverLogRaw(int level, const char *msg);
void serverLogFromHandler(int level, const char *msg);
void usage(void);
void updateDictResizePolicy(void);
int htNeedsResize(dict *dict);
void populateCommandTable(void);
void resetCommandTableStats(void);
2013-06-28 11:08:03 -04:00
void adjustOpenFilesLimit(void);
void closeListeningSockets(int unlink_unix_socket);
void updateCachedTime(void);
void resetServerStats(void);
unsigned int getLRUClock(void);
const char *evictPolicyToString(void);
#define RESTART_SERVER_NONE 0
#define RESTART_SERVER_GRACEFULLY (1<<0) /* Do proper shutdown. */
#define RESTART_SERVER_CONFIG_REWRITE (1<<1) /* CONFIG REWRITE before restart.*/
int restartServer(int flags, mstime_t delay);
/* Set data type */
robj *setTypeCreate(sds value);
int setTypeAdd(robj *subject, sds value);
int setTypeRemove(robj *subject, sds value);
int setTypeIsMember(robj *subject, sds value);
setTypeIterator *setTypeInitIterator(robj *subject);
void setTypeReleaseIterator(setTypeIterator *si);
int setTypeNext(setTypeIterator *si, sds *sdsele, int64_t *llele);
sds setTypeNextObject(setTypeIterator *si);
int setTypeRandomElement(robj *setobj, sds *sdsele, int64_t *llele);
unsigned long setTypeRandomElements(robj *set, unsigned long count, robj *aux_set);
unsigned long setTypeSize(const robj *subject);
void setTypeConvert(robj *subject, int enc);
/* Hash data type */
2016-04-25 09:39:33 -04:00
#define HASH_SET_TAKE_FIELD (1<<0)
#define HASH_SET_TAKE_VALUE (1<<1)
#define HASH_SET_COPY 0
2012-01-03 01:14:10 -05:00
void hashTypeConvert(robj *o, int enc);
void hashTypeTryConversion(robj *subject, robj **argv, int start, int end);
void hashTypeTryObjectEncoding(robj *subject, robj **o1, robj **o2);
int hashTypeExists(robj *o, sds key);
int hashTypeDelete(robj *o, sds key);
unsigned long hashTypeLength(const robj *o);
hashTypeIterator *hashTypeInitIterator(robj *subject);
void hashTypeReleaseIterator(hashTypeIterator *hi);
int hashTypeNext(hashTypeIterator *hi);
2012-01-03 01:14:10 -05:00
void hashTypeCurrentFromZiplist(hashTypeIterator *hi, int what,
unsigned char **vstr,
unsigned int *vlen,
long long *vll);
sds hashTypeCurrentFromHashTable(hashTypeIterator *hi, int what);
void hashTypeCurrentObject(hashTypeIterator *hi, int what, unsigned char **vstr, unsigned int *vlen, long long *vll);
sds hashTypeCurrentObjectNewSds(hashTypeIterator *hi, int what);
robj *hashTypeLookupWriteOrCreate(client *c, robj *key);
robj *hashTypeGetValueObject(robj *o, sds field);
2016-04-25 09:39:33 -04:00
int hashTypeSet(robj *o, sds field, sds value, int flags);
/* Pub / Sub */
int pubsubUnsubscribeAllChannels(client *c, int notify);
int pubsubUnsubscribeAllPatterns(client *c, int notify);
void freePubsubPattern(void *p);
int listMatchPubsubPattern(void *a, void *b);
int pubsubPublishMessage(robj *channel, robj *message);
/* Keyspace events notification */
void notifyKeyspaceEvent(int type, char *event, robj *key, int dbid);
int keyspaceEventsStringToFlags(char *classes);
sds keyspaceEventsFlagsToString(int flags);
/* Configuration */
void loadServerConfig(char *filename, char *options);
void appendServerSaveParams(time_t seconds, int changes);
void resetServerSaveParams(void);
struct rewriteConfigState; /* Forward declaration to export API. */
void rewriteConfigRewriteLine(struct rewriteConfigState *state, const char *option, sds line, int force);
int rewriteConfig(char *path);
/* db.c -- Keyspace access API */
int removeExpire(redisDb *db, robj *key);
void propagateExpire(redisDb *db, robj *key, int lazy);
int expireIfNeeded(redisDb *db, robj *key);
long long getExpire(redisDb *db, robj *key);
void setExpire(redisDb *db, robj *key, long long when);
robj *lookupKey(redisDb *db, robj *key, int flags);
robj *lookupKeyRead(redisDb *db, robj *key);
robj *lookupKeyWrite(redisDb *db, robj *key);
robj *lookupKeyReadOrReply(client *c, robj *key, robj *reply);
robj *lookupKeyWriteOrReply(client *c, robj *key, robj *reply);
robj *lookupKeyReadWithFlags(redisDb *db, robj *key, int flags);
#define LOOKUP_NONE 0
#define LOOKUP_NOTOUCH (1<<0)
void dbAdd(redisDb *db, robj *key, robj *val);
void dbOverwrite(redisDb *db, robj *key, robj *val);
void setKey(redisDb *db, robj *key, robj *val);
int dbExists(redisDb *db, robj *key);
robj *dbRandomKey(redisDb *db);
int dbSyncDelete(redisDb *db, robj *key);
int dbDelete(redisDb *db, robj *key);
robj *dbUnshareStringValue(redisDb *db, robj *key, robj *o);
#define EMPTYDB_NO_FLAGS 0 /* No flags. */
#define EMPTYDB_ASYNC (1<<0) /* Reclaim memory in another thread. */
long long emptyDb(int dbnum, int flags, void(callback)(void*));
int selectDb(client *c, int id);
void signalModifiedKey(redisDb *db, robj *key);
void signalFlushedDb(int dbid);
unsigned int getKeysInSlot(unsigned int hashslot, robj **keys, unsigned int count);
unsigned int countKeysInSlot(unsigned int hashslot);
unsigned int delKeysInSlot(unsigned int hashslot);
int verifyClusterConfigWithData(void);
void scanGenericCommand(client *c, robj *o, unsigned long cursor);
int parseScanCursorOrReply(client *c, robj *o, unsigned long *cursor);
void slotToKeyAdd(robj *key);
void slotToKeyDel(robj *key);
void slotToKeyFlush(void);
int dbAsyncDelete(redisDb *db, robj *key);
void emptyDbAsync(redisDb *db);
void slotToKeyFlushAsync(void);
size_t lazyfreeGetPendingObjectsCount(void);
/* API to get key arguments from commands */
int *getKeysFromCommand(struct redisCommand *cmd, robj **argv, int argc, int *numkeys);
void getKeysFreeResult(int *result);
int *zunionInterGetKeys(struct redisCommand *cmd,robj **argv, int argc, int *numkeys);
int *evalGetKeys(struct redisCommand *cmd, robj **argv, int argc, int *numkeys);
int *sortGetKeys(struct redisCommand *cmd, robj **argv, int argc, int *numkeys);
int *migrateGetKeys(struct redisCommand *cmd, robj **argv, int argc, int *numkeys);
2011-03-29 11:51:15 -04:00
/* Cluster */
void clusterInit(void);
unsigned short crc16(const char *buf, int len);
unsigned int keyHashSlot(char *key, int keylen);
void clusterCron(void);
void clusterPropagatePublish(robj *channel, robj *message);
void migrateCloseTimedoutSockets(void);
void clusterBeforeSleep(void);
2011-03-29 11:51:15 -04:00
/* Sentinel */
void initSentinelConfig(void);
void initSentinel(void);
void sentinelTimer(void);
char *sentinelHandleConfiguration(char **argv, int argc);
void sentinelIsRunning(void);
/* redis-check-rdb */
int redis_check_rdb(char *rdbfilename);
int redis_check_rdb_main(int argc, char **argv);
/* Scripting */
void scriptingInit(int setup);
int ldbRemoveChild(pid_t pid);
void ldbKillForkedSessions(void);
int ldbPendingChildren(void);
/* Blocked clients */
void processUnblockedClients(void);
void blockClient(client *c, int btype);
void unblockClient(client *c);
void replyToBlockedClientTimedOut(client *c);
int getTimeoutFromObjectOrReply(client *c, robj *object, mstime_t *timeout, int unit);
void disconnectAllBlockedClients(void);
/* expire.c -- Handling of expired keys */
void activeExpireCycle(int type);
/* evict.c -- maxmemory handling and LRU eviction. */
void evictionPoolAlloc(void);
#define LFU_INIT_VAL 5
unsigned long LFUGetTimeInMinutes(void);
uint8_t LFULogIncr(uint8_t value);
/* Git SHA1 */
char *redisGitSHA1(void);
char *redisGitDirty(void);
uint64_t redisBuildId(void);
/* Commands prototypes */
void authCommand(client *c);
void pingCommand(client *c);
void echoCommand(client *c);
void commandCommand(client *c);
void setCommand(client *c);
void setnxCommand(client *c);
void setexCommand(client *c);
void psetexCommand(client *c);
void getCommand(client *c);
void delCommand(client *c);
void unlinkCommand(client *c);
void existsCommand(client *c);
void setbitCommand(client *c);
void getbitCommand(client *c);
void bitfieldCommand(client *c);
void setrangeCommand(client *c);
void getrangeCommand(client *c);
void incrCommand(client *c);
void decrCommand(client *c);
void incrbyCommand(client *c);
void decrbyCommand(client *c);
void incrbyfloatCommand(client *c);
void selectCommand(client *c);
void randomkeyCommand(client *c);
void keysCommand(client *c);
void scanCommand(client *c);
void dbsizeCommand(client *c);
void lastsaveCommand(client *c);
void saveCommand(client *c);
void bgsaveCommand(client *c);
void bgrewriteaofCommand(client *c);
void shutdownCommand(client *c);
void moveCommand(client *c);
void renameCommand(client *c);
void renamenxCommand(client *c);
void lpushCommand(client *c);
void rpushCommand(client *c);
void lpushxCommand(client *c);
void rpushxCommand(client *c);
void linsertCommand(client *c);
void lpopCommand(client *c);
void rpopCommand(client *c);
void llenCommand(client *c);
void lindexCommand(client *c);
void lrangeCommand(client *c);
void ltrimCommand(client *c);
void typeCommand(client *c);
void lsetCommand(client *c);
void saddCommand(client *c);
void sremCommand(client *c);
void smoveCommand(client *c);
void sismemberCommand(client *c);
void scardCommand(client *c);
void spopCommand(client *c);
void srandmemberCommand(client *c);
void sinterCommand(client *c);
void sinterstoreCommand(client *c);
void sunionCommand(client *c);
void sunionstoreCommand(client *c);
void sdiffCommand(client *c);
void sdiffstoreCommand(client *c);
void sscanCommand(client *c);
void syncCommand(client *c);
void flushdbCommand(client *c);
void flushallCommand(client *c);
void sortCommand(client *c);
void lremCommand(client *c);
void rpoplpushCommand(client *c);
void infoCommand(client *c);
void mgetCommand(client *c);
void monitorCommand(client *c);
void expireCommand(client *c);
void expireatCommand(client *c);
void pexpireCommand(client *c);
void pexpireatCommand(client *c);
void getsetCommand(client *c);
void ttlCommand(client *c);
void touchCommand(client *c);
void pttlCommand(client *c);
void persistCommand(client *c);
void slaveofCommand(client *c);
void roleCommand(client *c);
void debugCommand(client *c);
void msetCommand(client *c);
void msetnxCommand(client *c);
void zaddCommand(client *c);
void zincrbyCommand(client *c);
void zrangeCommand(client *c);
void zrangebyscoreCommand(client *c);
void zrevrangebyscoreCommand(client *c);
void zrangebylexCommand(client *c);
void zrevrangebylexCommand(client *c);
void zcountCommand(client *c);
void zlexcountCommand(client *c);
void zrevrangeCommand(client *c);
void zcardCommand(client *c);
void zremCommand(client *c);
void zscoreCommand(client *c);
void zremrangebyscoreCommand(client *c);
void zremrangebylexCommand(client *c);
void multiCommand(client *c);
void execCommand(client *c);
void discardCommand(client *c);
void blpopCommand(client *c);
void brpopCommand(client *c);
void brpoplpushCommand(client *c);
void appendCommand(client *c);
void strlenCommand(client *c);
void zrankCommand(client *c);
void zrevrankCommand(client *c);
void hsetCommand(client *c);
void hsetnxCommand(client *c);
void hgetCommand(client *c);
void hmsetCommand(client *c);
void hmgetCommand(client *c);
void hdelCommand(client *c);
void hlenCommand(client *c);
void hstrlenCommand(client *c);
void zremrangebyrankCommand(client *c);
void zunionstoreCommand(client *c);
void zinterstoreCommand(client *c);
void zscanCommand(client *c);
void hkeysCommand(client *c);
void hvalsCommand(client *c);
void hgetallCommand(client *c);
void hexistsCommand(client *c);
void hscanCommand(client *c);
void configCommand(client *c);
void hincrbyCommand(client *c);
void hincrbyfloatCommand(client *c);
void subscribeCommand(client *c);
void unsubscribeCommand(client *c);
void psubscribeCommand(client *c);
void punsubscribeCommand(client *c);
void publishCommand(client *c);
void pubsubCommand(client *c);
void watchCommand(client *c);
void unwatchCommand(client *c);
void clusterCommand(client *c);
void restoreCommand(client *c);
void migrateCommand(client *c);
void askingCommand(client *c);
void readonlyCommand(client *c);
void readwriteCommand(client *c);
void dumpCommand(client *c);
void objectCommand(client *c);
void clientCommand(client *c);
void evalCommand(client *c);
void evalShaCommand(client *c);
void scriptCommand(client *c);
void timeCommand(client *c);
void bitopCommand(client *c);
void bitcountCommand(client *c);
void bitposCommand(client *c);
void replconfCommand(client *c);
void waitCommand(client *c);
void geoencodeCommand(client *c);
void geodecodeCommand(client *c);
void georadiusByMemberCommand(client *c);
void georadiusCommand(client *c);
void geoaddCommand(client *c);
void geohashCommand(client *c);
void geoposCommand(client *c);
void geodistCommand(client *c);
void pfselftestCommand(client *c);
void pfaddCommand(client *c);
void pfcountCommand(client *c);
void pfmergeCommand(client *c);
void pfdebugCommand(client *c);
void latencyCommand(client *c);
2016-03-06 07:44:24 -05:00
void moduleCommand(client *c);
void securityWarningCommand(client *c);
#if defined(__GNUC__)
void *calloc(size_t count, size_t size) __attribute__ ((deprecated));
void free(void *ptr) __attribute__ ((deprecated));
void *malloc(size_t size) __attribute__ ((deprecated));
void *realloc(void *ptr, size_t size) __attribute__ ((deprecated));
#endif
/* Debugging stuff */
void _serverAssertWithInfo(const client *c, const robj *o, const char *estr, const char *file, int line);
void _serverAssert(const char *estr, const char *file, int line);
void _serverPanic(const char *msg, const char *file, int line);
2011-11-24 09:47:26 -05:00
void bugReportStart(void);
void serverLogObjectDebugInfo(const robj *o);
void sigsegvHandler(int sig, siginfo_t *info, void *secret);
sds genRedisInfoString(char *section);
2012-03-27 05:47:51 -04:00
void enableWatchdog(int period);
void disableWatchdog(void);
void watchdogScheduleSignal(int period);
2015-07-26 09:17:43 -04:00
void serverLogHexDump(int level, char *descr, void *value, size_t len);
int memtest_preserving_test(unsigned long *m, size_t bytes, int passes);
#define redisDebug(fmt, ...) \
printf("DEBUG %s:%d > " fmt "\n", __FILE__, __LINE__, __VA_ARGS__)
#define redisDebugMark() \
printf("-- MARK %s:%d --\n", __FILE__, __LINE__)
#endif