Redis——源码分析之redis-server
概要
最近一直尝试去看点心东西，但又没有目标，想到之前计划要看的Redis源码，早上搭建了环境。代码是在Linux redhat6.5下托管着，在vmware下使用eclipse粘贴复制很不方便，遂使用xmanager工具配合eclipse来使用。
事前准备
- xmanager
- eclipse(for c/c++)
安装
- 安装xmanager就是一路next，没有什么特别需要注意的。就是在最终虚拟化一个linux界面的时候，要选择gnome-session --dispaly %$DISPLAY
- eclipse的安装跟启动参考上一篇博文
代码解析
redis UML时序图
1.入口函数redis.c#main()
2.初始化服务器参数
int main(int argc, char **argv) {
struct timeval tv;
/* We need to initialize our libraries, and the server configuration. */
#ifdef INIT_SETPROCTITLE_REPLACEMENT
spt_init(argc, argv);
#endif
setlocale(LC_COLLATE,"");
zmalloc_enable_thread_safeness();
zmalloc_set_oom_handler(redisOutOfMemoryHandler);
srand(time(NULL)^getpid());
gettimeofday(&tv,NULL);
dictSetHashFunctionSeed(tv.tv_sec^tv.tv_usec^getpid());
server.sentinel_mode = checkForSentinelMode(argc,argv);
initServerConfig();
.....
}3. initServerConfig()设置服务器默认值
void initServerConfig(void) {
int j;
getRandomHexChars(server.runid,REDIS_RUN_ID_SIZE);
server.configfile = NULL;
server.hz = REDIS_DEFAULT_HZ;
server.runid[REDIS_RUN_ID_SIZE] = '\0';
server.arch_bits = (sizeof(long) == 8) ? 64 : 32;
server.port = REDIS_SERVERPORT;
server.tcp_backlog = REDIS_TCP_BACKLOG;
server.bindaddr_count = 0;
server.unixsocket = NULL;
server.unixsocketperm = REDIS_DEFAULT_UNIX_SOCKET_PERM;
server.ipfd_count = 0;
server.sofd = -1;
server.dbnum = REDIS_DEFAULT_DBNUM;
server.verbosity = REDIS_DEFAULT_VERBOSITY;
server.maxidletime = REDIS_MAXIDLETIME;
server.tcpkeepalive = REDIS_DEFAULT_TCP_KEEPALIVE;
server.active_expire_enabled = 1;
server.client_max_querybuf_len = REDIS_MAX_QUERYBUF_LEN;
server.saveparams = NULL;
server.loading = 0;
server.logfile = zstrdup(REDIS_DEFAULT_LOGFILE);
server.syslog_enabled = REDIS_DEFAULT_SYSLOG_ENABLED;
server.syslog_ident = zstrdup(REDIS_DEFAULT_SYSLOG_IDENT);
server.syslog_facility = LOG_LOCAL0;
server.daemonize = REDIS_DEFAULT_DAEMONIZE;
server.aof_state = REDIS_AOF_OFF;
server.aof_fsync = REDIS_DEFAULT_AOF_FSYNC;
server.aof_no_fsync_on_rewrite = REDIS_DEFAULT_AOF_NO_FSYNC_ON_REWRITE;
server.aof_rewrite_perc = REDIS_AOF_REWRITE_PERC;
server.aof_rewrite_min_size = REDIS_AOF_REWRITE_MIN_SIZE;
server.aof_rewrite_base_size = 0;
server.aof_rewrite_scheduled = 0;
server.aof_last_fsync = time(NULL);
server.aof_rewrite_time_last = -1;
server.aof_rewrite_time_start = -1;
server.aof_lastbgrewrite_status = REDIS_OK;
server.aof_delayed_fsync = 0;
server.aof_fd = -1;
server.aof_selected_db = -1; /* Make sure the first time will not match */
server.aof_flush_postponed_start = 0;
server.aof_rewrite_incremental_fsync = REDIS_DEFAULT_AOF_REWRITE_INCREMENTAL_FSYNC;
server.aof_load_truncated = REDIS_DEFAULT_AOF_LOAD_TRUNCATED;
server.pidfile = zstrdup(REDIS_DEFAULT_PID_FILE);
server.rdb_filename = zstrdup(REDIS_DEFAULT_RDB_FILENAME);
server.aof_filename = zstrdup(REDIS_DEFAULT_AOF_FILENAME);
server.requirepass = NULL;
server.rdb_compression = REDIS_DEFAULT_RDB_COMPRESSION;
server.rdb_checksum = REDIS_DEFAULT_RDB_CHECKSUM;
server.stop_writes_on_bgsave_err = REDIS_DEFAULT_STOP_WRITES_ON_BGSAVE_ERROR;
server.activerehashing = REDIS_DEFAULT_ACTIVE_REHASHING;
server.notify_keyspace_events = 0;
server.maxclients = REDIS_MAX_CLIENTS;
server.bpop_blocked_clients = 0;
server.maxmemory = REDIS_DEFAULT_MAXMEMORY;
server.maxmemory_policy = REDIS_DEFAULT_MAXMEMORY_POLICY;
server.maxmemory_samples = REDIS_DEFAULT_MAXMEMORY_SAMPLES;
server.hash_max_ziplist_entries = REDIS_HASH_MAX_ZIPLIST_ENTRIES;
server.hash_max_ziplist_value = REDIS_HASH_MAX_ZIPLIST_VALUE;
server.list_max_ziplist_entries = REDIS_LIST_MAX_ZIPLIST_ENTRIES;
server.list_max_ziplist_value = REDIS_LIST_MAX_ZIPLIST_VALUE;
server.set_max_intset_entries = REDIS_SET_MAX_INTSET_ENTRIES;
server.zset_max_ziplist_entries = REDIS_ZSET_MAX_ZIPLIST_ENTRIES;
server.zset_max_ziplist_value = REDIS_ZSET_MAX_ZIPLIST_VALUE;
server.hll_sparse_max_bytes = REDIS_DEFAULT_HLL_SPARSE_MAX_BYTES;
server.shutdown_asap = 0;
server.repl_ping_slave_period = REDIS_REPL_PING_SLAVE_PERIOD;
server.repl_timeout = REDIS_REPL_TIMEOUT;
server.repl_min_slaves_to_write = REDIS_DEFAULT_MIN_SLAVES_TO_WRITE;
server.repl_min_slaves_max_lag = REDIS_DEFAULT_MIN_SLAVES_MAX_LAG;
server.cluster_enabled = 0;
server.cluster_node_timeout = REDIS_CLUSTER_DEFAULT_NODE_TIMEOUT;
server.cluster_migration_barrier = REDIS_CLUSTER_DEFAULT_MIGRATION_BARRIER;
server.cluster_slave_validity_factor = REDIS_CLUSTER_DEFAULT_SLAVE_VALIDITY;
server.cluster_require_full_coverage = REDIS_CLUSTER_DEFAULT_REQUIRE_FULL_COVERAGE;
server.cluster_configfile = zstrdup(REDIS_DEFAULT_CLUSTER_CONFIG_FILE);
server.lua_caller = NULL;
server.lua_time_limit = REDIS_LUA_TIME_LIMIT;
server.lua_client = NULL;
server.lua_timedout = 0;
server.migrate_cached_sockets = dictCreate(&migrateCacheDictType,NULL);
server.next_client_id = 1; /* Client IDs, start from 1 .*/
server.loading_process_events_interval_bytes = (1024*1024*2);
server.lruclock = getLRUClock();
resetServerSaveParams();
appendServerSaveParams(60*60,1); /* save after 1 hour and 1 change */
appendServerSaveParams(300,100); /* save after 5 minutes and 100 changes */
appendServerSaveParams(60,10000); /* save after 1 minute and 10000 changes */
/* Replication related */
server.masterauth = NULL;
server.masterhost = NULL;
server.masterport = 6379;
server.master = NULL;
server.cached_master = NULL;
server.repl_master_initial_offset = -1;
server.repl_state = REDIS_REPL_NONE;
server.repl_syncio_timeout = REDIS_REPL_SYNCIO_TIMEOUT;
server.repl_serve_stale_data = REDIS_DEFAULT_SLAVE_SERVE_STALE_DATA;
server.repl_slave_ro = REDIS_DEFAULT_SLAVE_READ_ONLY;
server.repl_down_since = 0; /* Never connected, repl is down since EVER. */
server.repl_disable_tcp_nodelay = REDIS_DEFAULT_REPL_DISABLE_TCP_NODELAY;
server.repl_diskless_sync = REDIS_DEFAULT_REPL_DISKLESS_SYNC;
server.repl_diskless_sync_delay = REDIS_DEFAULT_REPL_DISKLESS_SYNC_DELAY;
server.slave_priority = REDIS_DEFAULT_SLAVE_PRIORITY;
server.master_repl_offset = 0;
/* Replication partial resync backlog */
server.repl_backlog = NULL;
server.repl_backlog_size = REDIS_DEFAULT_REPL_BACKLOG_SIZE;
server.repl_backlog_histlen = 0;
server.repl_backlog_idx = 0;
server.repl_backlog_off = 0;
server.repl_backlog_time_limit = REDIS_DEFAULT_REPL_BACKLOG_TIME_LIMIT;
server.repl_no_slaves_since = time(NULL);
/* Client output buffer limits */
for (j = 0; j < REDIS_CLIENT_TYPE_COUNT; j++)
server.client_obuf_limits[j] = clientBufferLimitsDefaults[j];
/* Double constants initialization */
R_Zero = 0.0;
R_PosInf = 1.0/R_Zero;
R_NegInf = -1.0/R_Zero;
R_Nan = R_Zero/R_Zero;
/* Command table -- we initiialize it here as it is part of the
* initial configuration, since command names may be changed via
* redis.conf using the rename-command directive. */
server.commands = dictCreate(&commandTableDictType,NULL);
server.orig_commands = dictCreate(&commandTableDictType,NULL);
populateCommandTable();
server.delCommand = lookupCommandByCString("del");
server.multiCommand = lookupCommandByCString("multi");
server.lpushCommand = lookupCommandByCString("lpush");
server.lpopCommand = lookupCommandByCString("lpop");
server.rpopCommand = lookupCommandByCString("rpop");
/* Slow log */
server.slowlog_log_slower_than = REDIS_SLOWLOG_LOG_SLOWER_THAN;
server.slowlog_max_len = REDIS_SLOWLOG_MAX_LEN;
/* Latency monitor */
server.latency_monitor_threshold = REDIS_DEFAULT_LATENCY_MONITOR_THRESHOLD;
/* Debugging */
server.assert_failed = "";
server.assert_file = "";
server.assert_line = 0;
server.bug_report_start = 0;
server.watchdog_period = 0;
} void loadServerConfig(char *filename, char *options) {
sds config = sdsempty();
char buf[REDIS_CONFIGLINE_MAX+1];
/* Load the file content */
if (filename) {
FILE *fp;
if (filename[0] == '-' && filename[1] == '\0') {
fp = stdin;
} else {
if ((fp = fopen(filename,"r")) == NULL) {
redisLog(REDIS_WARNING,
"Fatal error, can't open config file '%s'", filename);
exit(1);
}
}
while(fgets(buf,REDIS_CONFIGLINE_MAX+1,fp) != NULL)
config = sdscat(config,buf);
if (fp != stdin) fclose(fp);
}
/* Append the additional options */
if (options) {
config = sdscat(config,"\n");
config = sdscat(config,options);
}
loadServerConfigFromString(config);
sdsfree(config);
}5.loadDataFromDisk()，从RDB或者AOF文件中加载数据到内存中
void loadDataFromDisk(void) {
long long start = ustime();
if (server.aof_state == REDIS_AOF_ON) {
if (loadAppendOnlyFile(server.aof_filename) == REDIS_OK)
redisLog(REDIS_NOTICE,"DB loaded from append only file: %.3f seconds",(float)(ustime()-start)/1000000);
} else {
if (rdbLoad(server.rdb_filename) == REDIS_OK) {
redisLog(REDIS_NOTICE,"DB loaded from disk: %.3f seconds",
(float)(ustime()-start)/1000000);
} else if (errno != ENOENT) {
redisLog(REDIS_WARNING,"Fatal error loading the DB: %s. Exiting.",strerror(errno));
exit(1);
}
}
}6.aeMain函数，循环调度：调用linux系统epoll来优化调度作业
void aeMain(aeEventLoop *eventLoop) {
eventLoop->stop = 0;
while (!eventLoop->stop) {
if (eventLoop->beforesleep != NULL)
eventLoop->beforesleep(eventLoop);
aeProcessEvents(eventLoop, AE_ALL_EVENTS);
}
}7.aeProcessEvents函数返回时间的进程ID
int aeProcessEvents(aeEventLoop *eventLoop, int flags)
{
int processed = 0, numevents;
/* Nothing to do? return ASAP */
if (!(flags & AE_TIME_EVENTS) && !(flags & AE_FILE_EVENTS)) return 0;
/* Note that we want call select() even if there are no
* file events to process as long as we want to process time
* events, in order to sleep until the next time event is ready
* to fire. */
if (eventLoop->maxfd != -1 ||
((flags & AE_TIME_EVENTS) && !(flags & AE_DONT_WAIT))) {
int j;
aeTimeEvent *shortest = NULL;
struct timeval tv, *tvp;
if (flags & AE_TIME_EVENTS && !(flags & AE_DONT_WAIT))
shortest = aeSearchNearestTimer(eventLoop);
if (shortest) {
long now_sec, now_ms;
/* Calculate the time missing for the nearest
* timer to fire. */
aeGetTime(&now_sec, &now_ms);
tvp = &tv;
tvp->tv_sec = shortest->when_sec - now_sec;
if (shortest->when_ms < now_ms) {
tvp->tv_usec = ((shortest->when_ms+1000) - now_ms)*1000;
tvp->tv_sec --;
} else {
tvp->tv_usec = (shortest->when_ms - now_ms)*1000;
}
if (tvp->tv_sec < 0) tvp->tv_sec = 0;
if (tvp->tv_usec < 0) tvp->tv_usec = 0;
} else {
/* If we have to check for events but need to return
* ASAP because of AE_DONT_WAIT we need to set the timeout
* to zero */
if (flags & AE_DONT_WAIT) {
tv.tv_sec = tv.tv_usec = 0;
tvp = &tv;
} else {
/* Otherwise we can block */
tvp = NULL; /* wait forever */
}
}
numevents = aeApiPoll(eventLoop, tvp);
for (j = 0; j < numevents; j++) {
aeFileEvent *fe = &eventLoop->events[eventLoop->fired[j].fd];
int mask = eventLoop->fired[j].mask;
int fd = eventLoop->fired[j].fd;
int rfired = 0;
/* note the fe->mask & mask & ... code: maybe an already processed
* event removed an element that fired and we still didn't
* processed, so we check if the event is still valid. */
if (fe->mask & mask & AE_READABLE) {
rfired = 1;
fe->rfileProc(eventLoop,fd,fe->clientData,mask);
}
if (fe->mask & mask & AE_WRITABLE) {
if (!rfired || fe->wfileProc != fe->rfileProc)
fe->wfileProc(eventLoop,fd,fe->clientData,mask);
}
processed++;
}
}
/* Check time events */
if (flags & AE_TIME_EVENTS)
processed += processTimeEvents(eventLoop);
return processed; /* return the number of processed file/time events */
}8.processTimeEvents函数，进程时间事件，用来获取当前要执行的事件信息
static int processTimeEvents(aeEventLoop *eventLoop) {
int processed = 0;
aeTimeEvent *te;
long long maxId;
time_t now = time(NULL);
/* If the system clock is moved to the future, and then set back to the
* right value, time events may be delayed in a random way. Often this
* means that scheduled operations will not be performed soon enough.
*
* Here we try to detect system clock skews, and force all the time
* events to be processed ASAP when this happens: the idea is that
* processing events earlier is less dangerous than delaying them
* indefinitely, and practice suggests it is. */
if (now < eventLoop->lastTime) {
te = eventLoop->timeEventHead;
while(te) {
te->when_sec = 0;
te = te->next;
}
}
eventLoop->lastTime = now;
te = eventLoop->timeEventHead;
maxId = eventLoop->timeEventNextId-1;
while(te) {
long now_sec, now_ms;
long long id;
if (te->id > maxId) {
te = te->next;
continue;
}
aeGetTime(&now_sec, &now_ms);
if (now_sec > te->when_sec ||
(now_sec == te->when_sec && now_ms >= te->when_ms))
{
int retval;
id = te->id;
retval = te->timeProc(eventLoop, id, te->clientData);
processed++;
/* After an event is processed our time event list may
* no longer be the same, so we restart from head.
* Still we make sure to don't process events registered
* by event handlers itself in order to don't loop forever.
* To do so we saved the max ID we want to handle.
*
* FUTURE OPTIMIZATIONS:
* Note that this is NOT great algorithmically. Redis uses
* a single time event so it's not a problem but the right
* way to do this is to add the new elements on head, and
* to flag deleted elements in a special way for later
* deletion (putting references to the nodes to delete into
* another linked list). */
if (retval != AE_NOMORE) {
aeAddMillisecondsToNow(retval,&te->when_sec,&te->when_ms);
} else {
aeDeleteTimeEvent(eventLoop, id);
}
te = eventLoop->timeEventHead;
} else {
te = te->next;
}
}
return processed;
}9.aeDeleteEventLoop()，释放调用事件占用的资源
void aeDeleteEventLoop(aeEventLoop *eventLoop) {
aeApiFree(eventLoop);
zfree(eventLoop->events);
zfree(eventLoop->fired);
zfree(eventLoop);
}10.DEBUG调试下Console上打印的log信息如下：
21716:C 11 Apr 21:02:01.163 # Warning: no config file specified, using the default config. In order to specify a config file use /home/project/redis-3.0.7/src/redis-server /path/to/redis.conf
21716:M 11 Apr 21:02:03.252 * Increased maximum number of open files to 10032 (it was originally set to 4096).
_._
_.-``__ ''-._
_.-`` `. `_. ''-._ Redis 3.0.7 (00000000/0) 64 bit
.-`` .-```. ```\/ _.,_ ''-._
( ' , .-` | `, ) Running in standalone mode
|`-._`-...-` __...-.``-._|'` _.-'| Port: 6379
| `-._ `._ / _.-' | PID: 21716
`-._ `-._ `-./ _.-' _.-'
|`-._`-._ `-.__.-' _.-'_.-'|
| `-._`-._ _.-'_.-' | http://redis.io
`-._ `-._`-.__.-'_.-' _.-'
|`-._`-._ `-.__.-' _.-'_.-'|
| `-._`-._ _.-'_.-' |
`-._ `-._`-.__.-'_.-' _.-'
`-._ `-.__.-' _.-'
`-._ _.-'
`-.__.-'
21716:M 11 Apr 21:02:35.698 # WARNING: The TCP backlog setting of 511 cannot be enforced because /proc/sys/net/core/somaxconn is set to the lower value of 128.
21716:M 11 Apr 21:07:03.749 # Server started, Redis version 3.0.7
21716:M 11 Apr 21:07:27.383 # WARNING overcommit_memory is set to 0! Background save may fail under low memory condition. To fix this issue add 'vm.overcommit_memory = 1' to /etc/sysctl.conf and then reboot or run the command 'sysctl vm.overcommit_memory=1' for this to take effect.
21716:M 11 Apr 21:07:27.383 # WARNING you have Transparent Huge Pages (THP) support enabled in your kernel. This will create latency and memory usage issues with Redis. To fix this issue run the command 'echo never > /sys/kernel/mm/transparent_hugepage/enabled' as root, and add it to your /etc/rc.local in order to retain the setting after a reboot. Redis must be restarted after THP is disabled.
21716:M 11 Apr 21:09:34.633 * The server is now ready to accept connections on port 6379