A reimplementation of blocking operation internals.

[redis.git] / src / redis.h

diff --git a/src/redis.h b/src/redis.h
index 3b9d4e78f7cf8d141d353bf9b0ff8810c3d55f66..24efef57b6c8910b96b040494324def67546d833 100644 (file)
--- a/src/redis.h
+++ b/src/redis.h
@@ -38,11 +38,13 @@
 #define REDIS_ERR               -1
 
 /* Static server configuration */
 #define REDIS_ERR               -1
 
 /* Static server configuration */

+#define REDIS_HZ                100     /* Time interrupt calls/sec. */

 #define REDIS_SERVERPORT        6379    /* TCP port */
 #define REDIS_MAXIDLETIME       0       /* default client timeout: infinite */
 #define REDIS_DEFAULT_DBNUM     16
 #define REDIS_CONFIGLINE_MAX    1024
 #define REDIS_EXPIRELOOKUPS_PER_CRON    10 /* lookup 10 expires per loop */
 #define REDIS_SERVERPORT        6379    /* TCP port */
 #define REDIS_MAXIDLETIME       0       /* default client timeout: infinite */
 #define REDIS_DEFAULT_DBNUM     16
 #define REDIS_CONFIGLINE_MAX    1024
 #define REDIS_EXPIRELOOKUPS_PER_CRON    10 /* lookup 10 expires per loop */

+#define REDIS_EXPIRELOOKUPS_TIME_PERC   25 /* CPU max % for keys collection */

 #define REDIS_MAX_WRITE_PER_EVENT (1024*64)
 #define REDIS_SHARED_SELECT_CMDS 10
 #define REDIS_SHARED_INTEGERS 10000
 #define REDIS_MAX_WRITE_PER_EVENT (1024*64)
 #define REDIS_SHARED_SELECT_CMDS 10
 #define REDIS_SHARED_INTEGERS 10000


@@ -54,10 +56,10 @@
 #define REDIS_SLOWLOG_LOG_SLOWER_THAN 10000
 #define REDIS_SLOWLOG_MAX_LEN 128
 #define REDIS_MAX_CLIENTS 10000
 #define REDIS_SLOWLOG_LOG_SLOWER_THAN 10000
 #define REDIS_SLOWLOG_MAX_LEN 128
 #define REDIS_MAX_CLIENTS 10000

-
+#define REDIS_AUTHPASS_MAX_LEN 512
+#define REDIS_DEFAULT_SLAVE_PRIORITY 100

 #define REDIS_REPL_TIMEOUT 60
 #define REDIS_REPL_PING_SLAVE_PERIOD 10
 #define REDIS_REPL_TIMEOUT 60
 #define REDIS_REPL_PING_SLAVE_PERIOD 10

-

 #define REDIS_RUN_ID_SIZE 40
 #define REDIS_OPS_SEC_SAMPLES 16
 
 #define REDIS_RUN_ID_SIZE 40
 #define REDIS_OPS_SEC_SAMPLES 16
 


@@ -82,6 +84,8 @@
 #define REDIS_CMD_NOSCRIPT  64              /* "s" flag */
 #define REDIS_CMD_RANDOM 128                /* "R" flag */
 #define REDIS_CMD_SORT_FOR_SCRIPT 256       /* "S" flag */
 #define REDIS_CMD_NOSCRIPT  64              /* "s" flag */
 #define REDIS_CMD_RANDOM 128                /* "R" flag */
 #define REDIS_CMD_SORT_FOR_SCRIPT 256       /* "S" flag */

+#define REDIS_CMD_LOADING 512               /* "l" flag */
+#define REDIS_CMD_STALE 1024                /* "t" flag */

 
 /* Object types */
 #define REDIS_STRING 0
 
 /* Object types */
 #define REDIS_STRING 0


@@ -163,8 +167,9 @@
 #define REDIS_REPL_NONE 0 /* No active replication */
 #define REDIS_REPL_CONNECT 1 /* Must connect to master */
 #define REDIS_REPL_CONNECTING 2 /* Connecting to master */
 #define REDIS_REPL_NONE 0 /* No active replication */
 #define REDIS_REPL_CONNECT 1 /* Must connect to master */
 #define REDIS_REPL_CONNECTING 2 /* Connecting to master */

-#define REDIS_REPL_TRANSFER 3 /* Receiving .rdb from master */
-#define REDIS_REPL_CONNECTED 4 /* Connected to master */
+#define REDIS_REPL_RECEIVE_PONG 3 /* Wait for PING reply */
+#define REDIS_REPL_TRANSFER 4 /* Receiving .rdb from master */
+#define REDIS_REPL_CONNECTED 5 /* Connected to master */

 
 /* Synchronous read timeout - slave side */
 #define REDIS_REPL_SYNCIO_TIMEOUT 5
 
 /* Synchronous read timeout - slave side */
 #define REDIS_REPL_SYNCIO_TIMEOUT 5


@@ -252,6 +257,11 @@
 #define REDIS_PROPAGATE_AOF 1
 #define REDIS_PROPAGATE_REPL 2
 
 #define REDIS_PROPAGATE_AOF 1
 #define REDIS_PROPAGATE_REPL 2
 

+/* Using the following macro you can run code inside serverCron() with the
+ * specified period, specified in milliseconds.
+ * The actual resolution depends on REDIS_HZ. */
+#define run_with_period(_ms_) if (!(server.cronloops%((_ms_)/(1000/REDIS_HZ))))
+

 /* We can print the stacktrace, so our assert is defined this way: */
 #define redisAssertWithInfo(_c,_o,_e) ((_e)?(void)0 : (_redisAssertWithInfo(_c,_o,#_e,__FILE__,__LINE__),_exit(1)))
 #define redisAssert(_e) ((_e)?(void)0 : (_redisAssert(#_e,__FILE__,__LINE__),_exit(1)))
 /* We can print the stacktrace, so our assert is defined this way: */
 #define redisAssertWithInfo(_c,_o,_e) ((_e)?(void)0 : (_redisAssertWithInfo(_c,_o,#_e,__FILE__,__LINE__),_exit(1)))
 #define redisAssert(_e) ((_e)?(void)0 : (_redisAssert(#_e,__FILE__,__LINE__),_exit(1)))


@@ -290,6 +300,7 @@ 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) */
     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) */

+    dict *ready_keys;           /* Blocked keys that received a PUSH */

     dict *watched_keys;         /* WATCHED keys for MULTI/EXEC CAS */
     int id;
 } redisDb;
     dict *watched_keys;         /* WATCHED keys for MULTI/EXEC CAS */
     int id;
 } redisDb;


@@ -316,6 +327,22 @@ typedef struct blockingState {
                              * for BRPOPLPUSH. */
 } blockingState;
 
                              * for BRPOPLPUSH. */
 } blockingState;
 

+/* 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;
+

 /* With multiplexing we need to take per-clinet state.
  * Clients are taken in a liked list. */
 typedef struct redisClient {
 /* With multiplexing we need to take per-clinet state.
  * Clients are taken in a liked list. */
 typedef struct redisClient {


@@ -343,6 +370,7 @@ typedef struct redisClient {
     int repldbfd;           /* replication DB file descriptor */
     long repldboff;         /* replication DB file offset */
     off_t repldbsize;       /* replication DB file size */
     int repldbfd;           /* replication DB file descriptor */
     long repldboff;         /* replication DB file offset */
     off_t repldbsize;       /* replication DB file size */

+    int slave_listening_port; /* As configured with: SLAVECONF listening-port */

     multiState mstate;      /* MULTI/EXEC state */
     blockingState bpop;   /* blocking state */
     list *io_keys;          /* Keys this client is waiting to be loaded from the
     multiState mstate;      /* MULTI/EXEC state */
     blockingState bpop;   /* blocking state */
     list *io_keys;          /* Keys this client is waiting to be loaded from the


@@ -366,8 +394,10 @@ struct sharedObjectsStruct {
     *colon, *nullbulk, *nullmultibulk, *queued,
     *emptymultibulk, *wrongtypeerr, *nokeyerr, *syntaxerr, *sameobjecterr,
     *outofrangeerr, *noscripterr, *loadingerr, *slowscripterr, *bgsaveerr,
     *colon, *nullbulk, *nullmultibulk, *queued,
     *emptymultibulk, *wrongtypeerr, *nokeyerr, *syntaxerr, *sameobjecterr,
     *outofrangeerr, *noscripterr, *loadingerr, *slowscripterr, *bgsaveerr,

-    *roslaveerr, *oomerr, *plus, *messagebulk, *pmessagebulk, *subscribebulk,
+    *masterdownerr, *roslaveerr,
+    *oomerr, *plus, *messagebulk, *pmessagebulk, *subscribebulk,

     *unsubscribebulk, *psubscribebulk, *punsubscribebulk, *del, *rpop, *lpop,
     *unsubscribebulk, *psubscribebulk, *punsubscribebulk, *del, *rpop, *lpop,

+    *lpush,

     *select[REDIS_SHARED_SELECT_CMDS],
     *integers[REDIS_SHARED_INTEGERS],
     *mbulkhdr[REDIS_SHARED_BULKHDR_LEN], /* "*<value>\r\n" */
     *select[REDIS_SHARED_SELECT_CMDS],
     *integers[REDIS_SHARED_INTEGERS],
     *mbulkhdr[REDIS_SHARED_BULKHDR_LEN], /* "*<value>\r\n" */


@@ -572,6 +602,7 @@ struct redisServer {
     int arch_bits;              /* 32 or 64 depending on sizeof(long) */
     int cronloops;              /* Number of times the cron function run */
     char runid[REDIS_RUN_ID_SIZE+1];  /* ID always different at every exec. */
     int arch_bits;              /* 32 or 64 depending on sizeof(long) */
     int cronloops;              /* Number of times the cron function run */
     char runid[REDIS_RUN_ID_SIZE+1];  /* ID always different at every exec. */

+    int sentinel_mode;          /* True if this instance is a Sentinel. */

     /* Networking */
     int port;                   /* TCP listening port */
     char *bindaddr;             /* Bind address or NULL */
     /* Networking */
     int port;                   /* TCP listening port */
     char *bindaddr;             /* Bind address or NULL */


@@ -591,7 +622,8 @@ struct redisServer {
     off_t loading_loaded_bytes;
     time_t loading_start_time;
     /* Fast pointers to often looked up command */
     off_t loading_loaded_bytes;
     time_t loading_start_time;
     /* Fast pointers to often looked up command */

-    struct redisCommand *delCommand, *multiCommand, *lpushCommand;
+    struct redisCommand *delCommand, *multiCommand, *lpushCommand, *lpopCommand,
+                        *rpopCommand;

     /* Fields used only for stats */
     time_t stat_starttime;          /* Server start time */
     long long stat_numcommands;     /* Number of processed commands */
     /* Fields used only for stats */
     time_t stat_starttime;          /* Server start time */
     long long stat_numcommands;     /* Number of processed commands */


@@ -631,12 +663,15 @@ struct redisServer {
     off_t aof_current_size;         /* AOF current size. */
     int aof_rewrite_scheduled;      /* Rewrite once BGSAVE terminates. */
     pid_t aof_child_pid;            /* PID if rewriting process */
     off_t aof_current_size;         /* AOF current size. */
     int aof_rewrite_scheduled;      /* Rewrite once BGSAVE terminates. */
     pid_t aof_child_pid;            /* PID if rewriting process */

-    sds aof_rewrite_buf; /* buffer taken by parent during oppend only rewrite */
+    list *aof_rewrite_buf_blocks;   /* Hold changes during an AOF rewrite. */

     sds aof_buf;      /* AOF buffer, written before entering the event loop */
     int aof_fd;       /* File descriptor of currently selected AOF file */
     int aof_selected_db; /* Currently selected DB in AOF */
     time_t aof_flush_postponed_start; /* UNIX time of postponed AOF flush */
     time_t aof_last_fsync;            /* UNIX time of last fsync() */
     sds aof_buf;      /* AOF buffer, written before entering the event loop */
     int aof_fd;       /* File descriptor of currently selected AOF file */
     int aof_selected_db; /* Currently selected DB in AOF */
     time_t aof_flush_postponed_start; /* UNIX time of postponed AOF flush */
     time_t aof_last_fsync;            /* UNIX time of last fsync() */

+    time_t aof_rewrite_time_last;   /* Time used by last AOF rewrite run. */
+    time_t aof_rewrite_time_start;  /* Current AOF rewrite start time. */
+    int aof_lastbgrewrite_status;   /* REDIS_OK or REDIS_ERR */

     unsigned long aof_delayed_fsync;  /* delayed AOF fsync() counter */
     /* RDB persistence */
     long long dirty;                /* Changes to DB from the last save */
     unsigned long aof_delayed_fsync;  /* delayed AOF fsync() counter */
     /* RDB persistence */
     long long dirty;                /* Changes to DB from the last save */


@@ -648,6 +683,8 @@ struct redisServer {
     int rdb_compression;            /* Use compression in RDB? */
     int rdb_checksum;               /* Use RDB checksum? */
     time_t lastsave;                /* Unix time of last save succeeede */
     int rdb_compression;            /* Use compression in RDB? */
     int rdb_checksum;               /* Use RDB checksum? */
     time_t lastsave;                /* Unix time of last save succeeede */

+    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 lastbgsave_status;          /* REDIS_OK or REDIS_ERR */
     int stop_writes_on_bgsave_err;  /* Don't allow writes if can't BGSAVE */
     /* Propagation of commands in AOF / replication */
     int lastbgsave_status;          /* REDIS_OK or REDIS_ERR */
     int stop_writes_on_bgsave_err;  /* Don't allow writes if can't BGSAVE */
     /* Propagation of commands in AOF / replication */


@@ -661,12 +698,14 @@ struct redisServer {
     char *masterauth;               /* AUTH with this password with master */
     char *masterhost;               /* Hostname of master */
     int masterport;                 /* Port of master */
     char *masterauth;               /* AUTH with this password with master */
     char *masterhost;               /* Hostname of master */
     int masterport;                 /* Port of master */

-    int repl_ping_slave_period;     /* Master pings the salve every N seconds */
+    int repl_ping_slave_period;     /* Master pings the slave every N seconds */

     int repl_timeout;               /* Timeout after N seconds of master idle */
     redisClient *master;     /* Client that is master for this slave */
     int repl_syncio_timeout; /* Timeout for synchronous I/O calls */
     int repl_state;          /* Replication status if the instance is a slave */
     int repl_timeout;               /* Timeout after N seconds of master idle */
     redisClient *master;     /* Client that is master for this slave */
     int repl_syncio_timeout; /* Timeout for synchronous I/O calls */
     int repl_state;          /* Replication status if the instance is a slave */

-    off_t repl_transfer_left;  /* Bytes left reading .rdb  */
+    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 */
     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 */


@@ -674,6 +713,7 @@ struct redisServer {
     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_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 slave_priority;             /* Reported in INFO and used by Sentinel. */

     /* Limits */
     unsigned int maxclients;        /* Max number of simultaneous clients */
     unsigned long long maxmemory;   /* Max number of memory bytes to use */
     /* Limits */
     unsigned int maxclients;        /* Max number of simultaneous clients */
     unsigned long long maxmemory;   /* Max number of memory bytes to use */


@@ -682,9 +722,9 @@ struct redisServer {
     /* Blocked clients */
     unsigned int bpop_blocked_clients; /* Number of clients blocked by lists */
     list *unblocked_clients; /* list of clients to unblock before next loop */
     /* Blocked clients */
     unsigned int bpop_blocked_clients; /* Number of clients blocked by lists */
     list *unblocked_clients; /* list of clients to unblock before next loop */

+    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() */
     /* 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_dontsort;

     int sort_desc;
     int sort_alpha;
     int sort_bypattern;
     int sort_desc;
     int sort_alpha;
     int sort_bypattern;


@@ -897,7 +937,7 @@ int listTypeEqual(listTypeEntry *entry, robj *o);
 void listTypeDelete(listTypeEntry *entry);
 void listTypeConvert(robj *subject, int enc);
 void unblockClientWaitingData(redisClient *c);
 void listTypeDelete(listTypeEntry *entry);
 void listTypeConvert(robj *subject, int enc);
 void unblockClientWaitingData(redisClient *c);

-int handleClientsWaitingListPush(redisClient *c, robj *key, robj *ele);
+void handleClientsBlockedOnLists(void);

 void popGenericCommand(redisClient *c, int where);
 
 /* MULTI/EXEC/WATCH... */
 void popGenericCommand(redisClient *c, int where);
 
 /* MULTI/EXEC/WATCH... */


@@ -974,6 +1014,8 @@ int loadAppendOnlyFile(char *filename);
 void stopAppendOnly(void);
 int startAppendOnly(void);
 void backgroundRewriteDoneHandler(int exitcode, int bysignal);
 void stopAppendOnly(void);
 int startAppendOnly(void);
 void backgroundRewriteDoneHandler(int exitcode, int bysignal);

+void aofRewriteBufferReset(void);
+unsigned long aofRewriteBufferSize(void);

 
 /* Sorted sets data type */
 
 
 /* Sorted sets data type */
 


@@ -1102,6 +1144,12 @@ void clusterCron(void);
 clusterNode *getNodeByQuery(redisClient *c, struct redisCommand *cmd, robj **argv, int argc, int *hashslot, int *ask);
 void clusterPropagatePublish(robj *channel, robj *message);
 
 clusterNode *getNodeByQuery(redisClient *c, struct redisCommand *cmd, robj **argv, int argc, int *hashslot, int *ask);
 void clusterPropagatePublish(robj *channel, robj *message);
 

+/* Sentinel */
+void initSentinelConfig(void);
+void initSentinel(void);
+void sentinelTimer(void);
+char *sentinelHandleConfiguration(char **argv, int argc);
+

 /* Scripting */
 void scriptingInit(void);
 
 /* Scripting */
 void scriptingInit(void);
 


@@ -1244,6 +1292,9 @@ void evalCommand(redisClient *c);
 void evalShaCommand(redisClient *c);
 void scriptCommand(redisClient *c);
 void timeCommand(redisClient *c);
 void evalShaCommand(redisClient *c);
 void scriptCommand(redisClient *c);
 void timeCommand(redisClient *c);

+void bitopCommand(redisClient *c);
+void bitcountCommand(redisClient *c);
+void replconfCommand(redisClient *c);

 
 #if defined(__GNUC__)
 void *calloc(size_t count, size_t size) __attribute__ ((deprecated));
 
 #if defined(__GNUC__)
 void *calloc(size_t count, size_t size) __attribute__ ((deprecated));


@@ -1263,4 +1314,11 @@ sds genRedisInfoString(char *section);
 void enableWatchdog(int period);
 void disableWatchdog(void);
 void watchdogScheduleSignal(int period);
 void enableWatchdog(int period);
 void disableWatchdog(void);
 void watchdogScheduleSignal(int period);

+void redisLogHexDump(int level, char *descr, void *value, size_t len);
+
+#define redisDebug(fmt, ...) \
+    printf("DEBUG %s:%d > " fmt "\n", __FILE__, __LINE__, __VA_ARGS__)
+#define redisDebugMark() \
+    printf("-- MARK %s:%d --\n", __FILE__, __LINE__)
+

 #endif
 #endif