前些天一台redis机器硬盘写满了,主要是由于程序bug导致备份量激增,而恰好监控程序的通知机制也罢工了,于是第一次体验到了redis的罢工(只读不写)。
现在我们来看下在磁盘写满后redis的处理机制:
save流程:serverCron->rdbSaveBackground->rdbSave
save后流程:serverCron->backgroundSaveDoneHandler
上述流程产生的结果就是server.lastbgsave_status = REDIS_ERR,
受其影响,processCommand和luaRedisGenericCommand中判断如果是写操作,则直接返回REDIS_OK,而没有实际写入
1.rdbSave所有的写出错都会返回REDIS_ERR
int rdbSave(char *filename) {
dictIterator *di = NULL;
dictEntry *de;
char tmpfile[256];
char magic[10];
int j;
long long now = mstime();
FILE *fp;
rio rdb;
uint64_t cksum;
snprintf(tmpfile,256,"temp-%d.rdb", (int) getpid());
fp = fopen(tmpfile,"w");
if (!fp) {
redisLog(REDIS_WARNING, "Failed opening .rdb for saving: %s",
strerror(errno));
return REDIS_ERR;
}
rioInitWithFile(&rdb,fp);
if (server.rdb_checksum)
rdb.update_cksum = rioGenericUpdateChecksum;
snprintf(magic,sizeof(magic),"REDIS%04d",REDIS_RDB_VERSION);
if (rdbWriteRaw(&rdb,magic,9) == -1) goto werr;
for (j = 0; j < server.dbnum; j++) {
redisDb *db = server.db+j;
dict *d = db->dict;
if (dictSize(d) == 0) continue;
di = dictGetSafeIterator(d);
if (!di) {
fclose(fp);
return REDIS_ERR;
}
/* Write the SELECT DB opcode */
if (rdbSaveType(&rdb,REDIS_RDB_OPCODE_SELECTDB) == -1) goto werr;
if (rdbSaveLen(&rdb,j) == -1) goto werr;
/* Iterate this DB writing every entry */
while((de = dictNext(di)) != NULL) {
sds keystr = dictGetKey(de);
robj key, *o = dictGetVal(de);
long long expire;
initStaticStringObject(key,keystr);
expire = getExpire(db,&key);
if (rdbSaveKeyValuePair(&rdb,&key,o,expire,now) == -1) goto werr;
}
dictReleaseIterator(di);
}
di = NULL; /* So that we don't release it again on error. */
/* EOF opcode */
if (rdbSaveType(&rdb,REDIS_RDB_OPCODE_EOF) == -1) goto werr;
/* CRC64 checksum. It will be zero if checksum computation is disabled, the
* loading code skips the check in this case. */
cksum = rdb.cksum;
memrev64ifbe(&cksum);
if (rioWrite(&rdb,&cksum,8) == 0) goto werr;
/* Make sure data will not remain on the OS's output buffers */
if (fflush(fp) == EOF) goto werr;
if (fsync(fileno(fp)) == -1) goto werr;
if (fclose(fp) == EOF) goto werr;
/* Use RENAME to make sure the DB file is changed atomically only
* if the generate DB file is ok. */
if (rename(tmpfile,filename) == -1) {
redisLog(REDIS_WARNING,"Error moving temp DB file on the final destination: %s", strerror(errno));
unlink(tmpfile);
return REDIS_ERR;
}
redisLog(REDIS_NOTICE,"DB saved on disk");
server.dirty = 0;
server.lastsave = time(NULL);
server.lastbgsave_status = REDIS_OK;
return REDIS_OK;
werr:
fclose(fp);
unlink(tmpfile);
redisLog(REDIS_WARNING,"Write error saving DB on disk: %s", strerror(errno));
if (di) dictReleaseIterator(di);
return REDIS_ERR;
}
2.rdbSaveBackground中,如果子进程调用rdbsave返回REDIS_ERR,那么子进程exit(1)
int rdbSaveBackground(char *filename) {
pid_t childpid;
long long start;
if (server.rdb_child_pid != -1) return REDIS_ERR;
server.dirty_before_bgsave = server.dirty;
server.lastbgsave_try = time(NULL);
start = ustime();
if ((childpid = fork()) == 0) {
int retval;
/* Child */
closeListeningSockets(0);
redisSetProcTitle("redis-rdb-bgsave");
retval = rdbSave(filename);
if (retval == REDIS_OK) {
size_t private_dirty = zmalloc_get_private_dirty();
if (private_dirty) {
redisLog